© 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. 9651
    Prev
    Next
    INDEX
    Explanations

    potential issues or threats

    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
     some
    -0.09
    angler
    -0.09
    æŁIJ
    -0.09
     quand
    -0.09
     Things
    -0.09
     things
    -0.09
    çļĦæĺ¯
    -0.09
    çļĦäºĭæĥħ
    -0.08
    581
    -0.08
    unga
    -0.08
    POSITIVE LOGITS
    /all
    0.22
    ones
    0.21
    place
    0.17
     sort
    0.15
    /e
    0.15
     kind
    0.13
    THING
    0.13
    ht
    0.13
    onen
    0.12
    ting
    0.12
    Activations Density 0.025%

    No Known Activations