© 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. 12893
    Prev
    Next
    INDEX
    Explanations

    negative imperatives

    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
     hood
    -0.09
    .Raise
    -0.09
    ubber
    -0.09
     lax
    -0.09
    owi
    -0.08
     çİ
    -0.08
     redund
    -0.08
    .presentation
    -0.08
    .nlm
    -0.08
    волÑı
    -0.08
    POSITIVE LOGITS
     worry
    0.14
     sugar
    0.11
     disappoint
    0.11
     afraid
    0.11
    orry
    0.10
    pz
    0.10
     forget
    0.10
     censor
    0.10
     necessarily
    0.10
     prefixed
    0.10
    Activations Density 0.024%

    No Known Activations