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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57238
    Prev
    Next
    INDEX
    Explanations

    physical attributes, particularly relating to someone's 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
    atk
    -0.06
    ziej
    -0.06
    eer
    -0.06
    atan
    -0.06
    orie
    -0.06
     Cop
    -0.06
     æij
    -0.06
    .dex
    -0.06
    swer
    -0.06
    icter
    -0.06
    POSITIVE LOGITS
    egas
    0.07
    Äįan
    0.06
     penetr
    0.06
     pdata
    0.06
    _ascii
    0.06
     ฿
    0.06
    زÙĪ
    0.06
     tens
    0.06
    ÛĮÙĨÙĩ
    0.06
    opus
    0.06
    Activations Density 0.000%

    No Known Activations