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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 51979
    Prev
    Next
    INDEX
    Explanations

    understand and prepare

    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
     priorit
    -0.11
    vern
    -0.09
    äºĮäºĮäºĮäºĮ
    -0.09
    /filepath
    -0.09
    utta
    -0.08
     burden
    -0.08
    deen
    -0.08
    èµ·æĿ¥
    -0.08
    .PathVariable
    -0.08
    .Documents
    -0.08
    POSITIVE LOGITS
     carefully
    0.25
    ä»Ķ
    0.19
     careful
    0.18
     closely
    0.15
    care
    0.14
     ÑĤÑī
    0.14
     understand
    0.14
     properly
    0.13
     correctly
    0.13
     understands
    0.13
    Activations Density 0.019%

    No Known Activations