© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 185
    Prev
    Next
    INDEX
    Explanations

    undesirable flavors during

    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
     pigeon
    -0.11
     spine
    -0.11
    toast
    -0.10
     resp
    -0.10
     hull
    -0.10
     toast
    -0.10
     Crushing
    -0.10
    ç·
    -0.10
     cheeses
    -0.10
     Toast
    -0.09
    POSITIVE LOGITS
     meat
    0.27
     lean
    0.26
    èĤī
    0.24
     Meat
    0.24
     Lean
    0.20
    lean
    0.20
     thá»ĭt
    0.20
    Lean
    0.20
     мÑıÑģ
    0.19
     Ú¯ÙĪØ´
    0.19
    Activations Density 0.053%

    No Known Activations