© 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. 84079
    Prev
    Next
    INDEX
    Explanations

    commas to denote listings or separations in text

    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
    à¹Ĥ
    -0.07
    /portfolio
    -0.07
    mani
    -0.07
    ì§ĢëıĦ
    -0.07
    AGO
    -0.07
    kaar
    -0.07
    felt
    -0.07
    립
    -0.07
    _ctxt
    -0.07
    TriState
    -0.07
    POSITIVE LOGITS
    we
    0.07
     Must
    0.07
     recourse
    0.06
    Must
    0.06
    erval
    0.06
    ÏĦαι
    0.06
    ame
    0.06
    swer
    0.06
    requires
    0.06
    must
    0.05
    Activations Density 0.023%

    No Known Activations