© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 99158
    Prev
    Next
    INDEX
    Explanations

    references to academic conferences and proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    Negative Logits
     muff
    -0.06
    seau
    -0.06
    XX
    -0.06
     flap
    -0.06
    MD
    -0.06
    ó
    -0.06
    hog
    -0.05
    emsp
    -0.05
     stitch
    -0.05
    apter
    -0.05
    POSITIVE LOGITS
    ndl
    0.07
    jde
    0.07
    jiang
    0.07
    lä
    0.07
    Inlining
    0.06
    URA
    0.06
    ALSE
    0.06
    à¹īาà¸ķ
    0.06
    asley
    0.06
    δή
    0.06
    Activations Density 0.577%

    No Known Activations