© 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. 82102
    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
    itori
    -0.06
    branches
    -0.06
    Overrides
    -0.06
     also
    -0.06
     won
    -0.06
    iterals
    -0.06
     supervised
    -0.06
    égor
    -0.06
     Overs
    -0.06
     dis
    -0.06
    POSITIVE LOGITS
    ildo
    0.07
     %,
    0.07
     condol
    0.07
     bdsm
    0.06
    conda
    0.06
    .MouseAdapter
    0.06
    .Shared
    0.06
    ç»ĻæĪij
    0.06
     tôi
    0.06
    HeaderText
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.