© 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. 106901
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistical data

    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
    ä»ĺãģij
    -0.08
    eydi
    -0.06
    .sol
    -0.06
    á»ĵi
    -0.06
     Downs
    -0.06
    ẽ
    -0.06
     ÅĻÃŃ
    -0.06
     Dam
    -0.06
    iest
    -0.06
     stÄĽ
    -0.06
    POSITIVE LOGITS
    .sax
    0.07
    _exempt
    0.06
    acket
    0.06
    yük
    0.06
    vero
    0.06
     Lans
    0.06
    _invoke
    0.06
    eldorf
    0.06
    Kit
    0.06
     Dist
    0.06
    Activations Density 0.004%

    No Known Activations