Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 78392
    Prev
    Next
    INDEX
    Explanations

    expressions and actions related to physical performance and body language in acting

    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
    aln
    -0.07
    .scalablytyped
    -0.07
    elsing
    -0.06
    vard
    -0.06
     hiss
    -0.06
     bestselling
    -0.06
    chez
    -0.06
     yans
    -0.06
    aight
    -0.06
    å¤ĩ
    -0.06
    POSITIVE LOGITS
     raise
    0.07
     move
    0.07
    ä¿Ĭ
    0.07
     raising
    0.07
     Mov
    0.06
    Ñĩно
    0.06
     Cup
    0.06
     Pest
    0.06
     spread
    0.06
     Faul
    0.06
    Activations Density 0.030%

    No Known Activations