© 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. 53799
    Prev
    Next
    INDEX
    Explanations

    mentions of drugs and their effects or comparisons

    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
    ika
    -0.07
    indows
    -0.07
    pagen
    -0.06
    á»ĭ
    -0.06
    icari
    -0.06
     Naked
    -0.06
     Finished
    -0.06
    formats
    -0.06
    iros
    -0.06
    æĸĹ
    -0.06
    POSITIVE LOGITS
     components
    0.23
    components
    0.20
     component
    0.19
     Components
    0.19
     parts
    0.19
     COMPONENT
    0.17
    -components
    0.17
     individual
    0.17
    _components
    0.17
    component
    0.17
    Activations Density 0.159%

    No Known Activations