© 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. 18560
    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
    /stretch
    -0.08
    .remote
    -0.07
    erras
    -0.07
     barric
    -0.07
    .construct
    -0.07
    obl
    -0.07
     declines
    -0.06
    رخ
    -0.06
    ilit
    -0.06
    eer
    -0.06
    POSITIVE LOGITS
    ebin
    0.06
    raya
    0.06
     become
    0.06
     appart
    0.06
     couples
    0.06
     oneself
    0.06
    gaard
    0.05
    iture
    0.05
    onald
    0.05
    xFFFFFF
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.