© 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. 59303
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
     Kush
    -0.10
     fret
    -0.09
     familiar
    -0.09
    ä¸ĩ
    -0.09
     Caval
    -0.09
    İ·
    -0.09
     fres
    -0.09
    onz
    -0.08
    orate
    -0.08
    imate
    -0.08
    POSITIVE LOGITS
     know
    0.22
     knows
    0.18
    çŁ¥éģĵ
    0.16
    know
    0.15
     Know
    0.14
    çŁ¥
    0.14
     biết
    0.13
    Know
    0.13
     wissen
    0.12
    -know
    0.11
    Activations Density 0.007%

    No Known Activations