© 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. 56967
    Prev
    Next
    INDEX
    Explanations

    martial art techniques emphasized

    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
    nze
    -0.10
    izr
    -0.09
     fist
    -0.09
    avr
    -0.09
    _kv
    -0.09
    Pitch
    -0.09
    lue
    -0.09
    ãĥĭãĤ¢
    -0.09
    pitch
    -0.09
    umper
    -0.08
    POSITIVE LOGITS
     openings
    0.15
     jab
    0.15
     cir
    0.14
     orthodox
    0.13
    jab
    0.13
     Jab
    0.13
     fe
    0.12
     mobility
    0.12
     Cir
    0.12
     attacks
    0.11
    Activations Density 0.028%

    No Known Activations