© 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. 103968
    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
    elden
    -0.08
    ghost
    -0.07
    onde
    -0.07
    _ghost
    -0.07
    ãĥ«ãĥķ
    -0.07
    uml
    -0.07
    ãĥªãĥ¼
    -0.07
    odule
    -0.07
    cki
    -0.07
     ÙĨج
    -0.07
    POSITIVE LOGITS
     equipments
    0.07
     Brewer
    0.06
     pozn
    0.06
    ì¶ľ
    0.06
     koc
    0.06
     splitted
    0.05
    ulling
    0.05
     Crush
    0.05
    ylie
    0.05
    èĪ¬
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.