© 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. 507
    Prev
    Next
    INDEX
    Explanations

    first sip, indulgence

    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
     feather
    -0.10
    oice
    -0.09
    inces
    -0.09
     Parts
    -0.09
     tasty
    -0.09
     gutter
    -0.09
     finalized
    -0.09
     munch
    -0.09
    ilan
    -0.08
    thood
    -0.08
    POSITIVE LOGITS
     bite
    0.25
     fork
    0.23
     bites
    0.21
     Bite
    0.21
    fork
    0.19
    åı£
    0.18
     sip
    0.18
     mouth
    0.18
    bite
    0.18
     Fork
    0.17
    Activations Density 0.037%

    No Known Activations