© 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. 927
    Prev
    Next
    INDEX
    Explanations

    words related to types and classifications

    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
    iyan
    -0.07
    .override
    -0.07
    egg
    -0.07
    braco
    -0.07
    gers
    -0.07
    ivec
    -0.07
    бо
    -0.07
    riend
    -0.07
    untas
    -0.06
    è¨ĢãģĨ
    -0.06
    POSITIVE LOGITS
     of
    0.11
    etting
    0.07
    etta
    0.07
    ahead
    0.07
    /types
    0.06
    jac
    0.06
    /type
    0.06
    Ĥæķ°
    0.06
     Providence
    0.06
    ickness
    0.06
    Activations Density 0.021%

    No Known Activations