© 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. 50666
    Prev
    Next
    INDEX
    Explanations

    long run, short term, near future

    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
    ValueCollection
    -0.09
     Sabb
    -0.09
    <TSource
    -0.09
    ilk
    -0.09
    /tos
    -0.08
    /Area
    -0.08
    acent
    -0.08
    .bp
    -0.08
    -era
    -0.08
    stal
    -0.08
    POSITIVE LOGITS
     term
    0.28
     run
    0.22
    term
    0.20
    run
    0.20
    -term
    0.18
     Term
    0.18
    .run
    0.17
    Term
    0.16
    -run
    0.14
     TERM
    0.14
    Activations Density 0.022%

    No Known Activations