© 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. 51347
    Prev
    Next
    INDEX
    Explanations

    sperm and bred

    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
     Erotic
    -0.18
     erotik
    -0.16
     erotic
    -0.16
     erót
    -0.14
     Erot
    -0.14
     erotica
    -0.14
     Erotik
    -0.13
     seksi
    -0.13
    Erot
    -0.13
    Sexy
    -0.13
    POSITIVE LOGITS
    ince
    0.13
     anal
    0.12
     cum
    0.12
     Anal
    0.11
     rim
    0.11
     gang
    0.11
     jew
    0.11
    anal
    0.11
    Anal
    0.10
    forced
    0.10
    Activations Density 0.144%

    No Known Activations