© 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. 1363
    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
     Vulner
    -0.08
     vulnerability
    -0.07
    ocks
    -0.07
     vulnerable
    -0.06
    aker
    -0.06
    istr
    -0.06
    itet
    -0.05
     styl
    -0.05
     Noir
    -0.05
    oad
    -0.05
    POSITIVE LOGITS
    iek
    0.07
    erno
    0.07
    .VALUE
    0.07
    opak
    0.07
    IDTH
    0.07
    /Library
    0.07
    enin
    0.06
    ervo
    0.06
    aura
    0.06
    IES
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.