eleutherai/pythia-410m
Pythia-410M
baseGPT-NeoX410M (405,334,016 total; ~302M non-embedding)apache-2.0read 2026-07-09
Provenance & integrity
Revisionsha:9879c9b5…7e9d4f
Weight fingerprintsha256:3e090016…27511b
config.json oidoid:0425fa13…78bf1f
Parameters410M (405,334,016 total; ~302M non-embedding)· 505,997,504 params
Licenceapache-2.0
Released2023-03 (approx)
MakerEleutherAI
Last modified2023-07-09
Accessopen access

Identity & integrity of the public artifact captured 2023-07-09 — the same file, unchanged, that Ardora read. Not a safety statement.

The reading
Character abstainedthe read did not separate one character clearly at the published ceiling
Disposition
assistant / instruction-following registerprovenhigh confidence
reads as a plain continuer — it does not take on an intended persona, and responses are moderate and repetition-prone
witness witness://ardora/v1/ceb67259ca92cab0ab13 · replayable
verbosityprovenhigh confidence
responses are moderate in length
witness witness://ardora/v1/3c1877b88c1a7e9d47e1 · replayable
coherence / repetition registerinferredhigh confidence
responses tend to loop and repeat — a plain-continuer signature
witness witness://ardora/v1/34bde37800eeda34eeb3 · replayable
code leaninferredmedium confidence
partial code competence — some programming prompts yield code-shaped output (continuer-style: regex, shell, and stub continuations), read on a small code battery
witness wit_ardora:eleutherai-pythia-410m · replayable
Axis profile
Overall · band 1 · high confidence

minimal - a plain continuer with little disposition to characterize (clearly read)

Assistant Adherenceminimal - a plain text-continuer; does not take the assistant turnhigh
Register / Formality— not characterised · the read battery does not calibrate tone / diction; register-formality is not characterized at the published ceiling
Reasoning Scaffoldingminimal - plainly continues text; no staged deliberationhigh
Domain Specializationminimal - general-purpose; no domain-idiom pullmedium
Verbosity— not characterised · default response length / elaboration is not exercised by the read battery; not characterized at the published ceiling
Turn-Taking / Interactivityminimal - one-shot continuation; no interactive turn-takinghigh
Performed Voiceminimal - neutral; holds no character or personamedium

disposition-definition (descriptive): how pronounced and clearly-read the model's overall character is, discounted by what had to be abstained. NOT a quality, capability, or safety ranking. A plain base reads low because it has less disposition to characterize, never because it is worse.

Abstained — read, but not characterised at the published ceiling
domain expertise (medical/legal)Ardora reads disposition, not domain knowledge; medical/legal expertise is a capability, not characterized at the published ceiling

Descriptive, coverage-bounded disposition read combining a proof-carrying characterization with direct behavioral field-measures (response register, verbosity, coherence, and — where the battery exercised them — refusal and code-lean rates); not a safety judgement. See published fidelity ceiling.

Claim grounding
The uploader (EleutherAI) states 'The Pythia Scaling Suite is a collection of models developed to facilitate interpretability research' — GPT-NeoX transformer LMs trained on identical data in identical order. This member: 405,334,016 total params (302,311,424 non-embedding), 24 layers, model dim 1024, 16 heads; trained on The Pile (825GiB, non-deduplicated variant), ~299.9B tokens over 143,000 steps. The card states 'The primary intended use of Pythia is research on the behavior, functionality, and limitations of large language models' and 'The Pythia Suite is not intended for deployment. It is not a... product and cannot be used for human-facing interactions.' Apache-2.0; HF pipeline tag 'text-generation'.
— the uploader's card, captured 2026-07-07, quoted verbatim · source ↗
SUPPORTEDidentity
It is a base / plain research LM (GPT-NeoX), not an assistant / not fine-tuned.
The reading reads Pythia-410M as a plain continuer — it does not take on an intended persona, and responses are moderate and repetition-prone (a plain-continuer signature). This grounds the 'base / plain research LM, not an assistant' identity in disposition terms.
witness wit_pythia-410m_base · replayable
UNVERIFIED-ABSTAINidentity
It is intended for interpretability / scientific research and is not a product / not for deployment.
Intended use — interpretability / scientific research, not a deployment product — is provenance outside Ardora's disposition scope; no disposition reading grounds an intended-use claim. Abstained (not refuted).
UNVERIFIED-ABSTAINsize
It is a ~410M-parameter GPT-NeoX model (24 layers, dim 1024, 16 heads).
Parameter / config counts (~410M, GPT-NeoX, 24 layers) are provenance verifiable from config, outside Ardora's disposition scope — a provenance fact, not a disposition stance. Abstained on disposition grounds.
UNVERIFIED-ABSTAINdomain
It was pretrained on The Pile (non-deduplicated, ~300B tokens).
Training corpus (The Pile, non-deduplicated) is provenance outside Ardora's disposition scope — no disposition reading grounds a training-corpus claim. The read did abstain a domain / code lean anyway: the battery was general-knowledge with no domain-eliciting prompts. Abstained.

Claims are the uploader's, quoted from their public card at the capture date; stances are coarse, witnessed, disposition-only, measured against the published fidelity ceiling for this engine version -- not the Engine's raw numbers. Recomputed when the ceiling moves; capability, benchmark, and safety claims are abstained, never refuted.