© 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 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. 77280
    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
    åŃĺäºİ
    -0.07
    _Exception
    -0.07
    [ID
    -0.07
    idar
    -0.06
     Äij
    -0.06
    emark
    -0.06
    üh
    -0.06
     поÑģ
    -0.06
     Dud
    -0.06
    //**↵
    -0.06
    POSITIVE LOGITS
    alim
    0.07
    jac
    0.06
     upto
    0.06
     TBD
    0.06
     mileage
    0.06
     Turing
    0.06
     pretty
    0.06
    ansom
    0.06
     apprent
    0.06
    éric
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.