© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56249
    Prev
    Next
    INDEX
    Explanations

    questions, particularly those that seek clarification or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Question marks followed by a line break ("<<?>>" in the examples) that separate a question from its answer in a Q&A format.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OTHERWISE
    -0.07
    .opensource
    -0.07
    .star
    -0.06
    bose
    -0.06
    ãİ¡
    -0.06
    Star
    -0.06
    agua
    -0.06
     rozs
    -0.06
    Eye
    -0.06
    .sb
    -0.06
    POSITIVE LOGITS
     answer
    0.14
     Answer
    0.13
     answered
    0.11
     ANSW
    0.10
     answers
    0.10
    Answer
    0.10
     answering
    0.10
     Answers
    0.09
    answer
    0.09
    çŃĶæ¡Ī
    0.09
    Activations Density 0.018%

    No Known Activations