© 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. 72417
    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
    輪
    -0.07
    vat
    -0.07
     STDCALL
    -0.07
    /rss
    -0.07
     traumat
    -0.07
     aba
    -0.07
    amac
    -0.07
    _ASSUME
    -0.06
    Ø®ÛĮ
    -0.06
    alam
    -0.06
    POSITIVE LOGITS
    iper
    0.07
     Weekly
    0.07
     weekly
    0.07
     Coin
    0.06
    okie
    0.06
     /
    0.06
    shall
    0.06
    adol
    0.05
     circulating
    0.05
    å¥Ķ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.