© 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. 34519
    Prev
    Next
    INDEX
    Explanations

    to use, enjoy, charge

    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
    edor
    -0.09
     wield
    -0.09
     åĺ
    -0.09
    ysa
    -0.09
     procur
    -0.09
    .EntityFramework
    -0.09
    dish
    -0.08
    453
    -0.08
    818
    -0.08
    .SetString
    -0.08
    POSITIVE LOGITS
     hands
    0.13
     functionality
    0.11
    享
    0.11
    æĸ¹
    0.11
    asty
    0.10
     hygiene
    0.10
     containment
    0.10
     accessor
    0.10
     threaded
    0.10
     convenience
    0.10
    Activations Density 0.119%

    No Known Activations