© 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. 58889
    Prev
    Next
    INDEX
    Explanations

    email finds you well

    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
    lain
    -0.10
    mland
    -0.10
    tera
    -0.09
    nof
    -0.09
     Bowman
    -0.08
    aceut
    -0.08
    ehr
    -0.08
     Freund
    -0.08
    ɵ
    -0.08
    ittal
    -0.08
    POSITIVE LOGITS
     finds
    0.32
     find
    0.29
     Finds
    0.25
     found
    0.23
    .find
    0.23
    find
    0.22
     finding
    0.21
    æī¾åĪ°
    0.19
     FIND
    0.19
     catch
    0.19
    Activations Density 0.013%

    No Known Activations