© 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. 1266
    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
    Negative Logits
     ro
    -0.06
     Vij
    -0.06
    .bz
    -0.06
    lein
    -0.06
     Acc
    -0.06
     AU
    -0.06
    Campo
    -0.06
    ç±
    -0.06
     Boeh
    -0.06
     Esc
    -0.05
    POSITIVE LOGITS
    Ī
    0.09
     KeyCode
    0.07
    idar
    0.07
    ecom
    0.07
     veri
    0.07
    -pills
    0.06
    INST
    0.06
    urons
    0.06
    uforia
    0.06
    imentary
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.