© 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. 106270
    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
    -0.06
     &
    -0.06
     /
    -0.06
     t
    -0.05
     ar
    -0.05
     Larry
    -0.05
    ...↵
    -0.05
     electr
    -0.05
     Gur
    -0.05
     start
    -0.05
    POSITIVE LOGITS
     mdi
    0.09
    /REC
    0.09
    asco
    0.08
    NetMessage
    0.08
    .updateDynamic
    0.08
    ">//
    0.08
    oÅĻ
    0.08
     ziy
    0.08
    amespace
    0.08
    ForResource
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.