Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40569
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    emoc
    -0.07
    stk
    -0.07
    kbd
    -0.07
    ¦æĥħ
    -0.07
    ç¤
    -0.07
     Franken
    -0.07
    'gc
    -0.07
    ndl
    -0.06
    istrovstvÃŃ
    -0.06
     Wich
    -0.06
    POSITIVE LOGITS
    vik
    0.08
    ayi
    0.07
    BOT
    0.06
    bundles
    0.06
    bot
    0.06
     costing
    0.06
    Epoch
    0.06
     
    0.06
     setBackgroundImage
    0.05
    iet
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.