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

    Neuronpedia

    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. 94461
    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
    _HOOK
    -0.07
    Ľå»º
    -0.07
    ÙĪجÙĩ
    -0.07
    elles
    -0.06
    982
    -0.06
    meyi
    -0.06
    ă
    -0.06
    406
    -0.06
     ALPHA
    -0.06
    raki
    -0.06
    POSITIVE LOGITS
     whose
    0.07
    trinsic
    0.06
    ë°ķ
    0.06
     Venez
    0.06
     currently
    0.06
     performance
    0.06
    vae
    0.06
    ights
    0.06
    ÑĪÑĮ
    0.06
    codegen
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.