© 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. 78158
    Prev
    Next
    INDEX
    Explanations

    references to signed or autographed items

    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
    ozem
    -0.08
    812
    -0.07
     ç¿
    -0.06
    createFrom
    -0.06
    433
    -0.06
    .jsoup
    -0.06
    ãĤ·ãĥ§ãĥ³
    -0.06
     Elliot
    -0.06
    625
    -0.06
    ourt
    -0.06
    POSITIVE LOGITS
     UNUSED
    0.06
    /sign
    0.06
    uddled
    0.06
    ataka
    0.06
     signed
    0.06
    handleRequest
    0.06
    linger
    0.06
     Bid
    0.06
    _exports
    0.06
    ddy
    0.06
    Activations Density 0.004%

    No Known Activations