© 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. 60253
    Prev
    Next
    INDEX
    Explanations

    struck me is

    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
     Dana
    -0.10
    Rnd
    -0.09
    stamp
    -0.09
    ''''
    -0.09
     tastes
    -0.09
    $MESS
    -0.09
    ANJI
    -0.09
     бли
    -0.09
     Mour
    -0.09
    adx
    -0.09
    POSITIVE LOGITS
    令
    0.19
    让æĪij
    0.14
     caught
    0.14
     impress
    0.13
     seemed
    0.13
     tick
    0.13
     khiến
    0.12
     fasc
    0.12
     seem
    0.12
     interests
    0.12
    Activations Density 0.164%

    No Known Activations