© 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 EvalsExportsAPI 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. 82866
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal appearance and the way individuals present themselves

    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
    chwitz
    -0.07
    ogue
    -0.07
    ICON
    -0.07
     nÄĽk
    -0.06
    otte
    -0.06
    мага
    -0.06
    atha
    -0.06
    .lock
    -0.06
    ίδα
    -0.06
    ÑĢÑĥг
    -0.06
    POSITIVE LOGITS
    èĥ½
    0.06
    eph
    0.06
     attitude
    0.06
     reaction
    0.06
    à¥Ĥà¤Ł
    0.06
    ephir
    0.06
    æĬĬ
    0.06
     Aura
    0.05
     Rising
    0.05
     willingness
    0.05
    Activations Density 0.026%

    No Known Activations