© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77079
    Prev
    Next
    INDEX
    Explanations

    attributes related to physical characteristics, specifically eye and hair color options

    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
     Higher
    -0.08
    Higher
    -0.07
    higher
    -0.07
     higher
    -0.07
    ault
    -0.07
    strtolower
    -0.06
    еÑĢп
    -0.06
    aminer
    -0.06
    onec
    -0.06
    uer
    -0.06
    POSITIVE LOGITS
     blond
    0.10
     hair
    0.10
     blonde
    0.10
     fair
    0.08
     stub
    0.07
     Blond
    0.07
     Hair
    0.07
     brunette
    0.07
     Blonde
    0.07
    ungan
    0.07
    Activations Density 0.029%

    No Known Activations