© 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. 9-LLAMASCOPE-RES-131K
    11. 99182
    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
    achel
    -0.07
    roup
    -0.06
    olen
    -0.06
    ylko
    -0.06
    ucci
    -0.06
     chilling
    -0.06
     looph
    -0.06
    ezier
    -0.06
    otel
    -0.06
    getSource
    -0.06
    POSITIVE LOGITS
    ắt
    0.07
    ãĥ©ãĥ¼
    0.06
    laz
    0.06
    .Tool
    0.06
    ãĥ¼ãĥĭ
    0.06
    ean
    0.06
    jang
    0.06
    spb
    0.06
     subj
    0.05
    /devices
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.