© 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. 92392
    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
     magna
    -0.06
    `
    -0.06
    hit
    -0.06
    ед
    -0.06
    帯
    -0.05
    -0.05
     Chr
    -0.05
    Âłob
    -0.05
     mainstream
    -0.05
     ver
    -0.05
    POSITIVE LOGITS
     myself
    0.08
    让æĪij
    0.08
     saya
    0.08
    æĺ¯æĪij
    0.07
    Ìĥ
    0.07
    enville
    0.07
    _locals
    0.07
    ponsive
    0.07
    ulkan
    0.07
    enson
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.