© 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. 83058
    Prev
    Next
    INDEX
    Explanations

    financial metrics and market forecasts

    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
    zman
    -0.07
    forme
    -0.07
    _msgs
    -0.07
    culo
    -0.07
    //{{
    -0.07
    ebe
    -0.07
    _Lean
    -0.07
    CustomAttributes
    -0.07
     Hale
    -0.07
    dete
    -0.07
    POSITIVE LOGITS
     Markt
    0.06
     Market
    0.06
     market
    0.06
    Market
    0.06
    /xhtml
    0.06
    arket
    0.06
     cross
    0.06
     revenue
    0.06
    abin
    0.06
     haar
    0.06
    Activations Density 0.003%

    No Known Activations