© 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. 28206
    Prev
    Next
    INDEX
    Explanations

    degree modifiers followed by qualities

    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
    -Za
    -0.10
    (<?
    -0.10
    Å¡et
    -0.09
    atively
    -0.09
     ÑĤабли
    -0.09
    aneously
    -0.09
    RunWith
    -0.09
    arily
    -0.09
    _Tis
    -0.09
    -Clause
    -0.09
    POSITIVE LOGITS
    iness
    0.10
     griev
    0.10
    æł·çļĦ
    0.10
    thon
    0.09
    æľīçļĦ
    0.09
    ĬìĿĢ
    0.09
    555
    0.09
    .mime
    0.09
    å®ļçļĦ
    0.08
    -existing
    0.08
    Activations Density 0.118%

    No Known Activations