© 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. 87467
    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
    zet
    -0.07
     Aid
    -0.06
    åĭ
    -0.06
    essen
    -0.06
     itemprop
    -0.06
    Extern
    -0.06
    té
    -0.06
    еÑĢим
    -0.06
    Boom
    -0.06
    atcher
    -0.06
    POSITIVE LOGITS
    ozo
    0.08
    semicolon
    0.07
    amac
    0.06
    empo
    0.06
    ccount
    0.06
    dech
    0.06
    rescia
    0.06
    uggage
    0.06
    arro
    0.06
    svc
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.