© 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. 13238
    Prev
    Next
    INDEX
    Explanations

    peer-reviewed journals and SCI review

    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
    ISBN
    -0.12
     ISBN
    -0.12
    \Catalog
    -0.09
    ahas
    -0.09
    /ion
    -0.09
    ackle
    -0.09
     Gum
    -0.09
     Daily
    -0.09
    Dictionary
    -0.09
    Typed
    -0.08
    POSITIVE LOGITS
     journal
    0.29
     journals
    0.25
     Else
    0.20
     peer
    0.19
    Else
    0.19
     Journal
    0.19
    journal
    0.17
    peer
    0.16
     Wo
    0.16
     Thomson
    0.16
    Activations Density 0.069%

    No Known Activations