© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33937
    Prev
    Next
    INDEX
    Explanations

    monogamy or poly relationships

    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
     heterosexual
    -0.13
     homosexuality
    -0.12
     homosexual
    -0.12
     marrying
    -0.11
     homosex
    -0.10
     marry
    -0.10
     homosexuals
    -0.10
     homophobic
    -0.10
     corpus
    -0.09
     Indo
    -0.09
    POSITIVE LOGITS
     poly
    0.29
     Poly
    0.27
    Poly
    0.22
    poly
    0.22
    (poly
    0.18
    _poly
    0.18
    .poly
    0.17
     mon
    0.16
     jealousy
    0.15
     veto
    0.14
    Activations Density 0.079%

    No Known Activations