© 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. 44523
    Prev
    Next
    INDEX
    Explanations

    описание, на, зна, каж

    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
    ÑĪиб
    -0.12
    ÑģÑĤÑĢов
    -0.10
     amen
    -0.09
    ongs
    -0.09
    inition
    -0.08
    ruh
    -0.08
    ród
    -0.08
    TTY
    -0.08
    rve
    -0.08
    iliz
    -0.08
    POSITIVE LOGITS
    tm
    0.10
    hr
    0.10
     ÑĤом
    0.09
    м
    0.09
    db
    0.09
    %c
    0.09
    ickle
    0.09
    ce
    0.09
    ifer
    0.09
    prim
    0.09
    Activations Density 0.021%

    No Known Activations