© 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. 62955
    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
    artz
    -0.07
     REFERENCES
    -0.07
    座
    -0.06
    ìķĶ
    -0.06
    631
    -0.06
     tarn
    -0.06
    wt
    -0.06
     import
    -0.06
    ibs
    -0.06
    amet
    -0.06
    POSITIVE LOGITS
    OSH
    0.07
    utter
    0.06
     Floyd
    0.06
    ting
    0.06
     isAuthenticated
    0.06
    ữu
    0.06
     Elo
    0.06
    exus
    0.06
    Fuse
    0.06
     mort
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.