Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65504
    Prev
    Next
    INDEX
    Explanations

    describing personality traits

    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
     Erotik
    -0.09
    sexy
    -0.09
     Pornhub
    -0.09
     Sexy
    -0.09
    .synthetic
    -0.08
    ï½į
    -0.08
    надлеж
    -0.08
     erót
    -0.08
     Hüs
    -0.08
    ayd
    -0.08
    POSITIVE LOGITS
     Bis
    0.12
     willing
    0.11
    IQ
    0.11
    bis
    0.10
     somewhat
    0.10
     partial
    0.10
     poly
    0.09
     Narc
    0.09
     bis
    0.09
     manip
    0.09
    Activations Density 0.084%

    No Known Activations