© 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. 25463
    Prev
    Next
    INDEX
    Explanations

    `double` types in code

    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
     fors
    -0.09
     clos
    -0.09
    /cop
    -0.08
    (il
    -0.08
    istrar
    -0.08
     knockout
    -0.08
    вÑĢоп
    -0.08
    neo
    -0.08
     cps
    -0.08
     bene
    -0.08
    POSITIVE LOGITS
     result
    0.13
     temp
    0.12
     x
    0.11
     q
    0.11
     u
    0.10
     ans
    0.10
     tmp
    0.10
    797
    0.09
     w
    0.09
     fac
    0.09
    Activations Density 0.092%

    No Known Activations