© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 261
    Prev
    Next
    INDEX
    Explanations

    wrongness or trouble

    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
    UNUSED
    -0.11
    Unavailable
    -0.11
    .IsNotNull
    -0.09
     reco
    -0.09
     accomp
    -0.09
    ving
    -0.09
     sloppy
    -0.09
    ãĥĬãĥ«
    -0.09
    _unused
    -0.08
     fest
    -0.08
    POSITIVE LOGITS
     wrong
    0.80
    wrong
    0.62
     Wrong
    0.60
    Wrong
    0.55
     WRONG
    0.54
     incorrect
    0.45
    éĶĻ
    0.43
    _wrong
    0.42
     à¤Ĺलत
    0.36
     непÑĢавилÑĮ
    0.34
    Activations Density 0.175%

    No Known Activations