© 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. 43455
    Prev
    Next
    INDEX
    Explanations

    generative pre-trained Transformer

    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
    phan
    -0.09
     件
    -0.09
     cords
    -0.09
     Rek
    -0.09
     tslint
    -0.09
     vocab
    -0.08
    ocre
    -0.08
    15
    -0.08
    ingham
    -0.08
     Grace
    -0.08
    POSITIVE LOGITS
     gener
    0.13
     Chat
    0.10
    ÂĢÂĢ
    0.10
    ennon
    0.09
    itaire
    0.09
     indifferent
    0.09
     Sanctuary
    0.09
    itto
    0.09
    IZER
    0.09
    bart
    0.09
    Activations Density 0.027%

    No Known Activations