© 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. 21569
    Prev
    Next
    INDEX
    Explanations

    not typical or unusual

    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
    BILE
    -0.09
    abort
    -0.09
     tuyá»ĩt
    -0.09
    ovah
    -0.09
     Undefined
    -0.09
     hor
    -0.08
     amazingly
    -0.08
    _svc
    -0.08
     Hag
    -0.08
     оÑĤп
    -0.08
    POSITIVE LOGITS
     unusual
    0.36
     abnormal
    0.34
     odd
    0.27
    å¼Ĥ常
    0.27
     dev
    0.26
     anom
    0.23
     normal
    0.23
     irregular
    0.23
     usual
    0.22
    usual
    0.22
    Activations Density 0.152%

    No Known Activations