© 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. 21113
    Prev
    Next
    INDEX
    Explanations

    separation and breaking

    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
     subdiv
    -0.10
     disreg
    -0.10
     abolition
    -0.09
     subdivisions
    -0.09
    _elim
    -0.09
     surrender
    -0.09
     bypass
    -0.09
     descending
    -0.09
    Disposed
    -0.09
     dismant
    -0.08
    POSITIVE LOGITS
     separation
    0.35
    éĽ¢
    0.35
    èĦ±
    0.33
     away
    0.33
    离
    0.32
     tách
    0.29
     break
    0.29
     separ
    0.28
     separated
    0.27
    离å¼Ģ
    0.27
    Activations Density 0.175%

    No Known Activations