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

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126703
    Prev
    Next
    INDEX
    Explanations

    descriptors related to physical appearance and charm, especially in relation to actresses

    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
    raç
    -0.07
    elsing
    -0.06
    tual
    -0.06
    Ñĩин
    -0.06
    OB
    -0.06
    TZ
    -0.06
     visual
    -0.06
     Bent
    -0.06
     Pell
    -0.06
    ayet
    -0.06
    POSITIVE LOGITS
    ieri
    0.08
    <boost
    0.07
    emo
    0.07
     Ти
    0.06
    .GetAsync
    0.06
    .WriteString
    0.06
    stringValue
    0.06
    .FindAsync
    0.06
    /REC
    0.06
    -points
    0.06
    Activations Density 0.122%

    No Known Activations