© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13663
    Prev
    Next
    INDEX
    Explanations

    adhere to guidelines

    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
    Ø·ÙĨ
    -0.10
    _excerpt
    -0.09
    allo
    -0.09
    utra
    -0.09
    ejs
    -0.09
    ude
    -0.08
     Nem
    -0.08
    ersh
    -0.08
    à¸ĵ
    -0.08
     zwar
    -0.08
    POSITIVE LOGITS
     scr
    0.12
     strictly
    0.12
    ance
    0.12
    ents
    0.12
    psilon
    0.11
    严
    0.11
     Stick
    0.11
    strict
    0.11
     closely
    0.10
     strict
    0.10
    Activations Density 0.021%

    No Known Activations