Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44782
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    ä¸ĢäºĽ
    -0.18
    ä¸ĢåĢĭ
    -0.12
    ä¸Ģå¹´
    -0.11
    ä¸ĢçĤ¹
    -0.09
    orry
    -0.09
    ä¸Ģ
    -0.09
    pressions
    -0.09
     Pu
    -0.09
     different
    -0.09
     sle
    -0.09
    POSITIVE LOGITS
     these
    0.13
    oud
    0.12
    rend
    0.10
    atum
    0.09
    _many
    0.09
     many
    0.09
     eskort
    0.09
     Straw
    0.09
    /from
    0.09
    594
    0.09
    Activations Density 0.041%

    No Known Activations