© 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. 64258
    Prev
    Next
    INDEX
    Explanations

    appealing to Google

    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
     airl
    -0.12
     sued
    -0.10
     searches
    -0.09
     suing
    -0.09
     defendant
    -0.09
     plaintiff
    -0.09
     plaintiffs
    -0.08
     inference
    -0.08
     pleading
    -0.08
    ã
    -0.08
    POSITIVE LOGITS
     appeal
    0.35
     contest
    0.29
     Appeal
    0.28
     appealing
    0.26
     appeals
    0.25
     appealed
    0.24
     challenge
    0.24
     Contest
    0.24
    contest
    0.23
    Appe
    0.22
    Activations Density 0.062%

    No Known Activations