© 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. 50290
    Prev
    Next
    INDEX
    Explanations

    negative or bad descriptors

    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
     disgust
    -0.12
    utter
    -0.09
    æ¼ı
    -0.09
    å¾
    -0.09
     disgusted
    -0.09
    Impossible
    -0.09
     nud
    -0.09
     disgusting
    -0.09
    âĦĸâĦĸ
    -0.09
     Labrador
    -0.09
    POSITIVE LOGITS
     negative
    0.39
    negative
    0.33
     Negative
    0.31
    Negative
    0.31
    -negative
    0.27
    egative
    0.25
    _negative
    0.25
     bad
    0.24
    è´Ł
    0.23
     negatives
    0.21
    Activations Density 0.243%

    No Known Activations