© 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. 48878
    Prev
    Next
    INDEX
    Explanations

    before an action

    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
    uner
    -0.10
    ersh
    -0.09
     Vys
    -0.09
    247
    -0.09
     McMahon
    -0.09
    mana
    -0.09
    akh
    -0.09
     stare
    -0.08
     Nielsen
    -0.08
    _busy
    -0.08
    POSITIVE LOGITS
     ká»ĭp
    0.23
     even
    0.20
     ÑĥÑģп
    0.15
     opportunity
    0.14
     reaction
    0.14
    åıįåºĶ
    0.14
     fully
    0.14
     protest
    0.14
     warning
    0.14
     barely
    0.13
    Activations Density 0.020%

    No Known Activations