© 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. 15157
    Prev
    Next
    INDEX
    Explanations

    sample guides or manuals

    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
     bibli
    -0.12
     bibliography
    -0.12
    /books
    -0.11
     papers
    -0.10
     umb
    -0.10
     Papers
    -0.09
     Webseite
    -0.09
     newsletters
    -0.09
     Homepage
    -0.09
    papers
    -0.09
    POSITIVE LOGITS
     guide
    0.51
     Guide
    0.41
    guide
    0.37
    -guide
    0.35
    Guide
    0.35
     manual
    0.33
     GUIDE
    0.32
    _guide
    0.30
     guides
    0.30
    manual
    0.27
    Activations Density 0.184%

    No Known Activations