© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56326
    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
     Dayton
    -0.07
    apk
    -0.06
    éĢļ
    -0.06
    django
    -0.06
    umen
    -0.06
     CVS
    -0.06
    utut
    -0.06
    ickt
    -0.06
    opathy
    -0.06
    CTR
    -0.06
    POSITIVE LOGITS
     Michaels
    0.07
    _IMP
    0.07
    목
    0.07
     billing
    0.07
    ÅĻÃŃž
    0.06
     Az
    0.06
    ulumi
    0.06
     clouds
    0.06
     Baldwin
    0.06
    vault
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.