© 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. 108656
    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
     Ros
    -0.06
    die
    -0.06
    anza
    -0.06
    leg
    -0.06
     readily
    -0.05
    chez
    -0.05
    lem
    -0.05
    uros
    -0.05
     Zimmer
    -0.05
     Lamb
    -0.05
    POSITIVE LOGITS
    ä»ķ
    0.08
    awy
    0.07
    Å¡ov
    0.07
     specifier
    0.07
    коÑĢиÑģÑĤ
    0.07
    icast
    0.07
    afx
    0.07
    lluminate
    0.07
    ocity
    0.07
    uforia
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.