© 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. 28853
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or unexpected events

    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
    jsonp
    -0.07
    ga
    -0.07
    urgeon
    -0.07
    елÑĸ
    -0.07
    *pow
    -0.07
    ograd
    -0.07
    wolf
    -0.07
    ç»ĻæĪij
    -0.07
    elier
    -0.07
     darm
    -0.07
    POSITIVE LOGITS
     capture
    0.07
     encounter
    0.06
     enc
    0.06
     Pap
    0.06
     Conserv
    0.06
     bait
    0.06
    owers
    0.06
     æĵ
    0.06
     humane
    0.06
    enc
    0.06
    Activations Density 0.042%

    No Known Activations