© 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. 15-LLAMASCOPE-RES-131K
    11. 89981
    Prev
    Next
    INDEX
    Explanations

    words related to performing or showcasing abilities

    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
    ofday
    -0.07
    hape
    -0.07
    hood
    -0.06
    .codehaus
    -0.06
    utches
    -0.06
    raki
    -0.06
    uran
    -0.06
    ãĥ¼ãĥ«
    -0.06
    адки
    -0.06
    ç¡
    -0.06
    POSITIVE LOGITS
    ably
    0.07
     pi
    0.07
     Trot
    0.06
    521
    0.06
    mue
    0.06
    /assert
    0.06
    _pi
    0.06
    ograd
    0.06
    baar
    0.06
    ingly
    0.06
    Activations Density 0.005%

    No Known Activations