© 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. 53970
    Prev
    Next
    INDEX
    Explanations

    either...or, or not

    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
     withheld
    -0.14
     withholding
    -0.12
     withhold
    -0.11
    ne
    -0.11
     underestimated
    -0.10
     cầm
    -0.09
    íĥĪ
    -0.09
    ç¦ģæŃ¢
    -0.09
     unwilling
    -0.09
     BK
    -0.09
    POSITIVE LOGITS
     ignore
    0.47
     Ign
    0.45
     ignored
    0.42
    忽
    0.41
     ignoring
    0.40
     Ignore
    0.39
    ignore
    0.38
     ign
    0.38
     ignores
    0.37
     IGNORE
    0.36
    Activations Density 0.079%

    No Known Activations