© 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. 15085
    Prev
    Next
    INDEX
    Explanations

    actions, thoughts, or dialogue descriptions

    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
     aff
    -0.09
    isContained
    -0.09
    888
    -0.09
    æĪĴ
    -0.09
     Boeh
    -0.09
     tact
    -0.08
     appet
    -0.08
    zap
    -0.08
     Appet
    -0.08
     alleg
    -0.08
    POSITIVE LOGITS
     actions
    0.24
     Actions
    0.19
     action
    0.19
    actions
    0.17
     scene
    0.17
    Actions
    0.16
     dialogue
    0.16
    -actions
    0.15
    /actions
    0.15
    _actions
    0.15
    Activations Density 0.227%

    No Known Activations