© 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. 42876
    Prev
    Next
    INDEX
    Explanations

    subject to change or variation

    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
    izzo
    -0.09
     Cunningham
    -0.09
     Noon
    -0.09
     torture
    -0.08
     Fury
    -0.08
     Californ
    -0.08
     Howell
    -0.08
    ovich
    -0.08
    ODO
    -0.08
     Reyes
    -0.08
    POSITIVE LOGITS
     subject
    0.37
     Subject
    0.30
    subject
    0.28
    Subject
    0.27
     sujet
    0.24
     SUBJECT
    0.24
     may
    0.23
     subjected
    0.21
     liable
    0.20
    (subject
    0.19
    Activations Density 0.072%

    No Known Activations