© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106489
    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
    -0.07
     perfect
    -0.06
     je
    -0.06
     plan
    -0.06
    onas
    -0.06
    perfect
    -0.06
    Perfect
    -0.06
     Foo
    -0.06
     client
    -0.05
    fs
    -0.05
    POSITIVE LOGITS
     ÎĶε
    0.08
    /Peak
    0.07
    semblies
    0.07
    ummings
    0.07
     privile
    0.07
    _Lean
    0.07
    <decltype
    0.07
    Unmarshaller
    0.07
    üçük
    0.07
    /*č↵
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.