© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129756
    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
     à¤ķहत
    -0.07
    enschaft
    -0.06
    á»Ĩ
    -0.06
     cil
    -0.06
     desper
    -0.06
     IRC
    -0.06
    еж
    -0.06
    onda
    -0.06
     Peel
    -0.06
    jist
    -0.06
    POSITIVE LOGITS
    bie
    0.07
     surtout
    0.07
    /uploads
    0.06
    ones
    0.06
     Gratuit
    0.06
    bow
    0.06
    /inet
    0.06
    /cmd
    0.06
    saldo
    0.06
     leap
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.