© 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. 25457
    Prev
    Next
    INDEX
    Explanations

    lips or mouth proximity

    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
    çķĻ
    -0.10
     squeez
    -0.09
     inward
    -0.09
     Minute
    -0.09
     finger
    -0.09
    legen
    -0.09
     hinter
    -0.09
    ResponseStatus
    -0.08
     fing
    -0.08
     distr
    -0.08
    POSITIVE LOGITS
     mouth
    0.18
     lips
    0.17
    -mouth
    0.17
    åı£
    0.17
     mouths
    0.17
    åĺ´
    0.16
     Mouth
    0.15
    mouth
    0.15
     boca
    0.14
    emouth
    0.13
    Activations Density 0.026%

    No Known Activations