© 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. 16176
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pure" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    shelf
    -0.09
    orp
    -0.07
    mino
    -0.07
    sel
    -0.07
    perature
    -0.06
    lamp
    -0.06
    ote
    -0.06
    dale
    -0.06
    nie
    -0.06
    re
    -0.06
    POSITIVE LOGITS
    -blood
    0.11
    bred
    0.11
     Pure
    0.10
    /raw
    0.09
    blood
    0.09
    sts
    0.09
    pure
    0.09
    iy
    0.08
    auc
    0.08
    -syntax
    0.08
    Activations Density 0.009%

    No Known Activations