© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117250
    Prev
    Next
    INDEX
    Explanations

    references to clothing and the act of removing garments

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     dressed
    -0.07
    isos
    -0.06
    Ø®Ùħ
    -0.06
    closure
    -0.06
     Block
    -0.06
     block
    -0.06
     dress
    -0.06
    Closure
    -0.06
     Serve
    -0.06
     Hutch
    -0.06
    POSITIVE LOGITS
     airs
    0.07
    roof
    0.07
     Removed
    0.06
     remover
    0.06
     removal
    0.06
     remove
    0.06
     removed
    0.06
    remove
    0.06
    -remove
    0.06
     Emoji
    0.06
    Activations Density 0.013%

    No Known Activations