© 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. 62927
    Prev
    Next
    INDEX
    Explanations

    types of writing and reporting

    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
    .scalablytyped
    -0.13
    ANDOM
    -0.11
     manuscript
    -0.11
     Transcript
    -0.10
    tre
    -0.10
    ERM
    -0.09
     licensors
    -0.09
     tast
    -0.09
    _datos
    -0.09
    ettle
    -0.09
    POSITIVE LOGITS
     articles
    0.18
     blog
    0.15
     Articles
    0.14
     article
    0.14
     reports
    0.12
    æĸĩç«ł
    0.12
    articles
    0.12
     short
    0.12
    Articles
    0.12
     essays
    0.12
    Activations Density 0.095%

    No Known Activations