© 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. 62505
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to grooming and physical appearance

    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
     crunchy
    -0.06
    ácil
    -0.06
     глаза
    -0.06
    verture
    -0.06
    ÙĪاء
    -0.06
    enheim
    -0.06
     ÑģиÑĢ
    -0.06
     Gund
    -0.06
    iyel
    -0.06
    .eql
    -0.06
    POSITIVE LOGITS
     beard
    0.07
     ç¤
    0.07
     stub
    0.07
     razor
    0.07
     Beard
    0.07
     men
    0.07
     shaving
    0.07
    Kin
    0.07
     bar
    0.07
     period
    0.06
    Activations Density 0.015%

    No Known Activations