© 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. 1262
    Prev
    Next
    INDEX
    Explanations

    terms related to the prevention of sexual violence

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    vit
    -0.07
    .statistics
    -0.07
    Statistics
    -0.06
     Smarty
    -0.06
     Pell
    -0.06
    DataTask
    -0.06
    _seen
    -0.06
     Statistics
    -0.06
    Beam
    -0.06
    ifar
    -0.06
    POSITIVE LOGITS
     framework
    0.09
     model
    0.09
     Framework
    0.08
    Framework
    0.08
    ramework
    0.08
    framework
    0.08
    model
    0.07
    odel
    0.07
     Model
    0.07
     MODEL
    0.07
    Activations Density 0.044%

    No Known Activations