© 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. 71713
    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
    su
    -0.06
    éĢł
    -0.05
    /wiki
    -0.05
    holes
    -0.05
    amarin
    -0.05
     Chatt
    -0.05
     major
    -0.05
     Red
    -0.05
     å¯
    -0.05
    POSITIVE LOGITS
    ordion
    0.08
    æī¬
    0.08
    ogle
    0.08
    omanip
    0.07
    few
    0.07
    ï¿¥
    0.07
     bana
    0.07
    anlar
    0.07
     $($
    0.07
    upe
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.