© 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. 14373
    Prev
    Next
    INDEX
    Explanations

    stripper

    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
     Penis
    -0.11
     Rape
    -0.11
     raping
    -0.10
     homosex
    -0.10
     prostitute
    -0.10
     raped
    -0.10
     orgas
    -0.09
    .:.
    -0.09
    /***/
    -0.09
     penis
    -0.09
    POSITIVE LOGITS
     pole
    0.30
    pole
    0.26
     strip
    0.25
     stri
    0.24
     Pole
    0.24
     lap
    0.23
     poles
    0.22
     stripping
    0.21
     adult
    0.20
     Strip
    0.19
    Activations Density 0.061%

    No Known Activations