© 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. 44758
    Prev
    Next
    INDEX
    Explanations

    book titles

    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
     Scope
    -0.10
    ocrates
    -0.10
    Scope
    -0.10
    aten
    -0.10
     masked
    -0.09
     Living
    -0.09
    æĹ
    -0.09
     Mitar
    -0.09
    åĩºåĵģ
    -0.09
     writer
    -0.09
    POSITIVE LOGITS
     novel
    0.15
    Interpreter
    0.14
     catcher
    0.13
     Atlas
    0.13
     Fahrenheit
    0.12
     Kush
    0.12
    Stamped
    0.12
    ovel
    0.12
     Interpreter
    0.11
     Neu
    0.11
    Activations Density 0.081%

    No Known Activations