© 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. 5643
    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
    mé
    -0.07
     tém
    -0.06
     Progressive
    -0.06
    sei
    -0.06
     mé
    -0.06
    ÑģилÑĮ
    -0.06
     ìłĢ
    -0.06
     nues
    -0.06
    ecycle
    -0.06
    peg
    -0.06
    POSITIVE LOGITS
    estone
    0.08
    estro
    0.07
    eeper
    0.07
     lately
    0.07
    ingle
    0.07
    iming
    0.07
    ehr
    0.07
    å§ij
    0.07
    TestCategory
    0.07
    оз
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.