© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 764
    Prev
    Next
    INDEX
    Explanations

    fight or wrestle 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
     swagger
    -0.10
    害
    -0.10
    vez
    -0.10
     prostitu
    -0.09
     ank
    -0.09
     ê´
    -0.09
     Backbone
    -0.09
    744
    -0.08
     Peer
    -0.08
     Horny
    -0.08
    POSITIVE LOGITS
     fight
    0.19
     Fight
    0.16
     neither
    0.15
     fighting
    0.13
     fought
    0.12
    fight
    0.12
     боÑĢÑĮ
    0.11
     birbir
    0.11
     tit
    0.11
     combat
    0.11
    Activations Density 0.021%

    No Known Activations