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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34636
    Prev
    Next
    INDEX
    Explanations

    insults and profanity

    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
     fucked
    -0.13
     dicks
    -0.12
     fucks
    -0.12
     Fucked
    -0.12
     derp
    -0.12
     bullshit
    -0.12
     assh
    -0.11
     fart
    -0.11
     douche
    -0.11
     asshole
    -0.10
    POSITIVE LOGITS
     cre
    0.14
     sc
    0.14
     piece
    0.13
     mong
    0.12
     rat
    0.11
    worth
    0.11
    /li
    0.11
    -li
    0.11
    piece
    0.11
    picable
    0.11
    Activations Density 0.078%

    No Known Activations