© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    small apartment"}, {"late grandmother"}, {"the mall"}

    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
    ARSE
    -0.09
    lep
    -0.09
     Barbie
    -0.08
     extrem
    -0.08
    ubble
    -0.08
    esson
    -0.08
    ISR
    -0.08
     seedu
    -0.08
    rink
    -0.08
     cunt
    -0.08
    POSITIVE LOGITS
    antic
    0.09
    ÌĨ
    0.09
     topp
    0.08
     Widgets
    0.08
    OPS
    0.08
    arias
    0.08
     NGO
    0.08
     Stateless
    0.08
     oak
    0.08
    -widgets
    0.08
    Activations Density 0.167%

    No Known Activations