© 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 EvalsExportsinterp-engineNEWAPI 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. 38880
    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
    onal
    -0.07
    arel
    -0.07
    solete
    -0.07
    ourke
    -0.07
    abox
    -0.07
    ì´
    -0.07
    	Copyright
    -0.07
     вп
    -0.06
     Decomp
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
     leader
    0.07
    Leader
    0.07
     Leader
    0.06
    _leader
    0.06
    leader
    0.06
     lider
    0.06
    족
    0.06
    appropri
    0.06
     lÃŃder
    0.06
    رÙģت
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.