© 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. 22037
    Prev
    Next
    INDEX
    Explanations

    partners and 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
     marital
    -0.15
     matrimon
    -0.15
     marriages
    -0.14
     divorced
    -0.13
     marriage
    -0.12
     divor
    -0.11
     married
    -0.11
     Marriage
    -0.11
     divorce
    -0.11
    arend
    -0.10
    POSITIVE LOGITS
     partners
    0.41
     partner
    0.37
     Partner
    0.29
     паÑĢÑĤ
    0.27
    partner
    0.27
     Partners
    0.27
    Partner
    0.26
    _partner
    0.23
    partners
    0.22
    .partner
    0.20
    Activations Density 0.087%

    No Known Activations