© 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. 29888
    Prev
    Next
    INDEX
    Explanations

    varies slightly over time

    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
     circum
    -0.11
     Manip
    -0.11
    -volume
    -0.09
     Ar
    -0.09
     Tub
    -0.09
    Manip
    -0.09
     crater
    -0.09
    cap
    -0.09
     precip
    -0.09
    cks
    -0.08
    POSITIVE LOGITS
     slight
    0.18
    æ½®
    0.16
     pert
    0.15
     slightly
    0.13
    pert
    0.13
     subtle
    0.13
     Pert
    0.12
     bul
    0.12
     secular
    0.12
     oval
    0.12
    Activations Density 0.030%

    No Known Activations