© 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. 54941
    Prev
    Next
    INDEX
    Explanations

    sounds like

    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
    ä¸īä¸ī
    -0.09
    ãĤĥ
    -0.09
    egin
    -0.08
    .utf
    -0.08
     Leban
    -0.08
    swer
    -0.08
     sieve
    -0.08
     Appearance
    -0.08
     Scotia
    -0.08
     Sind
    -0.08
    POSITIVE LOGITS
     sounds
    0.75
     Sounds
    0.67
    Sounds
    0.66
    sounds
    0.62
     sounded
    0.51
     sound
    0.50
     sounding
    0.47
    sound
    0.39
     Sound
    0.38
    Sound
    0.35
    Activations Density 0.160%

    No Known Activations