© 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. 425
    Prev
    Next
    INDEX
    Explanations

    and powerful, averaging, leading

    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
     jugg
    -0.09
    dress
    -0.09
    èª
    -0.09
     ram
    -0.09
     Niet
    -0.09
     Industrial
    -0.09
    ugi
    -0.09
    äºĮäºĮäºĮäºĮ
    -0.09
    stÅĻÃŃ
    -0.09
    roje
    -0.09
    POSITIVE LOGITS
     performances
    0.13
     raw
    0.12
     explos
    0.11
     Electric
    0.11
     clutch
    0.11
     electric
    0.10
     aerial
    0.10
    raw
    0.10
     consistency
    0.10
     technical
    0.10
    Activations Density 0.060%

    No Known Activations