© 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. 17-LLAMASCOPE-RES-131K
    11. 69333
    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
    iment
    -0.07
     pre
    -0.06
    ampo
    -0.06
     Alb
    -0.06
    ulin
    -0.06
     Grund
    -0.06
    [rand
    -0.06
    Limits
    -0.06
     provid
    -0.05
     Freak
    -0.05
    POSITIVE LOGITS
    blr
    0.09
    iram
    0.09
     diseñador
    0.08
    gas
    0.08
    yonel
    0.08
    _HOR
    0.08
     navr
    0.08
    é¢ij次
    0.07
    batim
    0.07
    lfw
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.