© 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. 63907
    Prev
    Next
    INDEX
    Explanations

    she was or had

    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
     aff
    -0.10
     pref
    -0.09
     obese
    -0.09
     outgoing
    -0.09
    ols
    -0.09
     http
    -0.09
     dp
    -0.09
     antib
    -0.09
    GLE
    -0.09
    odyn
    -0.09
    POSITIVE LOGITS
    roz
    0.12
     inverted
    0.10
    ç¶Ń
    0.10
     upkeep
    0.10
     strength
    0.09
     intim
    0.09
     maint
    0.09
    iker
    0.09
     hon
    0.09
     constitution
    0.09
    Activations Density 0.054%

    No Known Activations