© 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. 34631
    Prev
    Next
    INDEX
    Explanations

    alphabets and scripts

    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
     franc
    -0.10
     ech
    -0.10
     slang
    -0.10
    è¯į
    -0.09
    éĿ
    -0.09
    canf
    -0.09
     Digit
    -0.09
    èĭ±èªŀ
    -0.09
    Abb
    -0.09
    crc
    -0.08
    POSITIVE LOGITS
     script
    0.21
     orth
    0.17
     characters
    0.16
     writing
    0.16
    _script
    0.15
     scripts
    0.15
     stroke
    0.14
    .script
    0.14
     transl
    0.14
     Cyril
    0.14
    Activations Density 0.117%

    No Known Activations