© 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. 61125
    Prev
    Next
    INDEX
    Explanations

    expressions and moments that elicit laughter or amusement

    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
    icolor
    -0.06
    Ñİн
    -0.06
    wrap
    -0.06
    691
    -0.06
     Courage
    -0.06
    .toCharArray
    -0.06
    Zone
    -0.06
    416
    -0.06
    urgence
    -0.06
    stvÃŃ
    -0.05
    POSITIVE LOGITS
     laughing
    0.10
     laughter
    0.10
     laughs
    0.08
     laugh
    0.08
    Laugh
    0.08
    -la
    0.08
     gigg
    0.08
    ç¬ij
    0.08
     laughed
    0.07
    oot
    0.07
    Activations Density 0.027%

    No Known Activations