© 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. 59530
    Prev
    Next
    INDEX
    Explanations

    cooking verbs

    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
    lord
    -0.09
     Vad
    -0.09
    ovich
    -0.08
     rins
    -0.08
    bow
    -0.08
    urat
    -0.08
    /ay
    -0.08
     cooled
    -0.08
     Ch
    -0.08
    hazi
    -0.08
    POSITIVE LOGITS
     bake
    0.27
     Bake
    0.24
     baking
    0.18
     baked
    0.18
     refriger
    0.13
    çĥ
    0.13
     incub
    0.13
    cook
    0.12
     cover
    0.12
     cook
    0.12
    Activations Density 0.019%

    No Known Activations