© 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. 56664
    Prev
    Next
    INDEX
    Explanations

    apply or prohibition

    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
     cih
    -0.09
     Dock
    -0.09
    ikh
    -0.08
     equ
    -0.08
     Infos
    -0.08
    eyse
    -0.08
     поба
    -0.08
    adla
    -0.08
    otify
    -0.08
    equals
    -0.08
    POSITIVE LOGITS
     applies
    0.63
     apply
    0.61
     applicable
    0.52
    apply
    0.50
     Applies
    0.47
     Apply
    0.47
    .apply
    0.45
    Apply
    0.44
    éģ©çĶ¨
    0.43
     applic
    0.42
    Activations Density 0.122%

    No Known Activations