© 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. 30352
    Prev
    Next
    INDEX
    Explanations

    barely, rarely, not very

    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
     Bauer
    -0.11
    arah
    -0.10
     Liberty
    -0.10
    orry
    -0.10
    è¿İ
    -0.09
    immel
    -0.09
    ounding
    -0.09
    UX
    -0.08
    Ë
    -0.08
     fewer
    -0.08
    POSITIVE LOGITS
     barely
    0.13
     above
    0.13
     Bare
    0.11
     able
    0.11
     percept
    0.11
     enough
    0.11
    -contained
    0.10
    bare
    0.10
     ><?
    0.10
    yyyy
    0.10
    Activations Density 0.018%

    No Known Activations