© 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. 60433
    Prev
    Next
    INDEX
    Explanations

    your/my followed by relationship terms

    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
     married
    -0.12
     divorced
    -0.11
     friendships
    -0.11
    daughter
    -0.11
     remar
    -0.11
    married
    -0.10
     acquaintance
    -0.10
     mistress
    -0.10
     divor
    -0.10
     marriages
    -0.10
    POSITIVE LOGITS
     partner
    0.35
     Partner
    0.27
    partner
    0.26
    Partner
    0.24
     partners
    0.24
    .partner
    0.21
     паÑĢÑĤ
    0.21
     significant
    0.19
    _partner
    0.19
    artner
    0.19
    Activations Density 0.077%

    No Known Activations