© 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. 17992
    Prev
    Next
    INDEX
    Explanations

    bes or bes followed by z

    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
    zap
    -0.10
    entar
    -0.09
    803
    -0.09
    h
    -0.09
    alez
    -0.09
    ench
    -0.09
     habit
    -0.09
     Wald
    -0.08
    inder
    -0.08
    è£ħç½®
    -0.08
    POSITIVE LOGITS
    poke
    0.13
    oins
    0.13
     bes
    0.13
    otted
    0.12
    itzer
    0.12
    erk
    0.11
     Bes
    0.11
    oin
    0.11
    onders
    0.11
    nard
    0.10
    Activations Density 0.027%

    No Known Activations