© 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. 57033
    Prev
    Next
    INDEX
    Explanations

    HTML/XML closing tags and structures

    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
    blr
    -0.06
    acio
    -0.06
     mö
    -0.06
    -handed
    -0.06
    fft
    -0.06
    äche
    -0.06
    enia
    -0.06
     Rub
    -0.06
    s
    -0.06
     handed
    -0.05
    POSITIVE LOGITS
     æĻ®éĢļ
    0.07
    /Peak
    0.07
    ----------------------------------------------------------------------↵
    0.07
    ÑĥÑĩа
    0.07
    .gwt
    0.07
    è¡
    0.07
    WithType
    0.07
     cigaret
    0.07
    WithName
    0.06
    ÑģилÑĮ
    0.06
    Activations Density 0.000%

    No Known Activations