© 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. 42124
    Prev
    Next
    INDEX
    Explanations

    select, put, design, remove

    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
     Choices
    -0.13
     choices
    -0.13
     Choice
    -0.11
     choice
    -0.11
     selected
    -0.11
    Choices
    -0.11
     chosen
    -0.10
    ItemSelected
    -0.10
    _choice
    -0.10
    -choice
    -0.10
    POSITIVE LOGITS
     deselect
    0.12
    wis
    0.11
     Wis
    0.11
    ajs
    0.10
    zcze
    0.09
     battles
    0.09
    EGIN
    0.09
     wisely
    0.09
     Dolphin
    0.09
    based
    0.09
    Activations Density 0.142%

    No Known Activations