© 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. 36976
    Prev
    Next
    INDEX
    Explanations

    digital footprints or visible streak

    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
    732
    -0.09
     inherited
    -0.09
    alin
    -0.09
    ekl
    -0.09
     Sé
    -0.09
    733
    -0.09
     vag
    -0.09
    plusplus
    -0.08
     fug
    -0.08
     assort
    -0.08
    POSITIVE LOGITS
     trail
    0.39
    trail
    0.31
     footprint
    0.30
     tracks
    0.30
     trails
    0.30
     Trail
    0.29
     wake
    0.29
    Trail
    0.27
     behind
    0.26
     mark
    0.25
    Activations Density 0.072%

    No Known Activations