© 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. 24669
    Prev
    Next
    INDEX
    Explanations

    complex bone structure and developed visual systems

    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
     legs
    -0.10
     limbs
    -0.10
     jag
    -0.10
     Hog
    -0.10
     blank
    -0.09
     Hans
    -0.09
    :
    -0.09
     nose
    -0.09
     Pier
    -0.09
     Lambert
    -0.09
    POSITIVE LOGITS
     oss
    0.13
     Structures
    0.11
     structures
    0.11
     paddle
    0.11
     possession
    0.10
     rud
    0.10
     vest
    0.10
     horny
    0.10
    Anal
    0.10
     заклад
    0.10
    Activations Density 0.060%

    No Known Activations