© 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. 38125
    Prev
    Next
    INDEX
    Explanations

    sunshine rate

    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
    ÂĢÂĢ
    -0.10
    izik
    -0.10
    aign
    -0.09
    ê°¤
    -0.09
    ÅĻÃŃz
    -0.09
    antar
    -0.09
    ÄįasÃŃ
    -0.09
    ŀĭ
    -0.08
     Ñįлек
    -0.08
    ansen
    -0.08
    POSITIVE LOGITS
    dit
    0.10
     Ñģолн
    0.09
     Ïĥκ
    0.09
    UV
    0.09
    829
    0.09
    irate
    0.08
     Mour
    0.08
    kie
    0.08
    Solar
    0.08
     sun
    0.08
    Activations Density 0.018%

    No Known Activations