© 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. 20428
    Prev
    Next
    INDEX
    Explanations

    apply warm damp cloth

    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
     Pes
    -0.10
     chalk
    -0.10
    atar
    -0.09
     Stap
    -0.09
     bush
    -0.09
     drying
    -0.09
     Pru
    -0.09
     breath
    -0.09
     lung
    -0.09
     healed
    -0.09
    POSITIVE LOGITS
     compress
    0.22
    æķ·
    0.16
     ice
    0.15
     applied
    0.15
     packs
    0.15
    compress
    0.14
     pack
    0.13
     пÑĢиклад
    0.13
     Packs
    0.13
     Ice
    0.12
    Activations Density 0.026%

    No Known Activations