© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33619
    Prev
    Next
    INDEX
    Explanations

    as it is

    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
     Dak
    -0.10
    ppt
    -0.09
    CanBe
    -0.09
     imposs
    -0.09
     rather
    -0.09
    ellig
    -0.09
     nên
    -0.09
    iales
    -0.08
    911
    -0.08
     wer
    -0.08
    POSITIVE LOGITS
    iner
    0.12
    è¿Ŀ
    0.12
    adaki
    0.11
     viol
    0.10
     ew
    0.10
     would
    0.10
     conflict
    0.09
    éģķ
    0.09
     Tune
    0.09
    alc
    0.09
    Activations Density 0.061%

    No Known Activations