© 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. 34010
    Prev
    Next
    INDEX
    Explanations

    lists of things

    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
    ä¹ĭä¸Ģ
    -0.11
    orp
    -0.09
    [rand
    -0.09
    éĤ£ä¸ª
    -0.09
    ä¸Ģ人
    -0.08
     biri
    -0.08
    *pow
    -0.08
     ambos
    -0.08
    cken
    -0.08
     both
    -0.08
    POSITIVE LOGITS
     several
    0.29
     bunch
    0.26
     Several
    0.21
    åĩłä¸ª
    0.20
    Several
    0.19
     beberapa
    0.17
     ÙħجÙħÙĪعة
    0.17
     sets
    0.17
    èĭ¥
    0.17
    ListOf
    0.16
    Activations Density 0.335%

    No Known Activations