© 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. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 37982
    Prev
    Next
    INDEX
    Explanations

    expressions and social cues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yosh
    -0.09
    ï½ľ
    -0.09
     Vent
    -0.09
    strup
    -0.09
    eli
    -0.09
     glo
    -0.09
     contrario
    -0.09
     pinch
    -0.08
    piler
    -0.08
    opia
    -0.08
    POSITIVE LOGITS
     pause
    0.18
     paused
    0.17
     tens
    0.15
     hesitation
    0.15
     expression
    0.15
    Pause
    0.15
     raises
    0.14
     expressions
    0.14
     looked
    0.14
     raise
    0.14
    Activations Density 0.027%

    No Known Activations