© 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. 63024
    Prev
    Next
    INDEX
    Explanations

    threats or strong reactions

    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
     fuck
    -0.10
     bitch
    -0.10
    862
    -0.10
     fucked
    -0.10
     asshole
    -0.10
    pees
    -0.10
     fucks
    -0.09
     cruel
    -0.09
     shit
    -0.09
     betr
    -0.09
    POSITIVE LOGITS
     insol
    0.11
     thinks
    0.11
     attitude
    0.10
     mouth
    0.10
    uddenly
    0.10
     yourself
    0.10
     fixation
    0.10
     patron
    0.09
    pra
    0.09
    anko
    0.09
    Activations Density 0.048%

    No Known Activations