© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5702
    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
    ovel
    -0.07
    ApiClient
    -0.06
    esa
    -0.06
    esthetic
    -0.06
     Wyn
    -0.06
    andal
    -0.06
     sweetness
    -0.06
     booty
    -0.06
    POSITE
    -0.06
    732
    -0.06
    POSITIVE LOGITS
     runtime
    0.07
     Clover
    0.07
    dea
    0.07
     herr
    0.06
    reno
    0.06
    _CMP
    0.06
    ocha
    0.06
    ë¬
    0.06
    BorderColor
    0.06
    discard
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.