© 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. 40067
    Prev
    Next
    INDEX
    Explanations

    insalata di pomodoro

    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
     prune
    -0.10
     gravy
    -0.10
     cloves
    -0.09
     sauces
    -0.09
    RuleContext
    -0.09
     ãĢĥ
    -0.09
     odense
    -0.09
    pcm
    -0.08
     cooking
    -0.08
    duct
    -0.08
    POSITIVE LOGITS
     salad
    0.27
     salads
    0.24
     Salad
    0.24
     bowl
    0.17
     iceberg
    0.17
     Ñģал
    0.17
     dressing
    0.16
     Wald
    0.16
     Sal
    0.15
     rom
    0.15
    Activations Density 0.032%

    No Known Activations