© 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. 423
    Prev
    Next
    INDEX
    Explanations

    acronyms, initialisms, compound words

    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
    eldon
    -0.10
    ninger
    -0.09
    gorithm
    -0.09
    andid
    -0.09
    ãĤº
    -0.08
    .scrollTo
    -0.08
    .forName
    -0.08
    tak
    -0.08
    itude
    -0.08
    egr
    -0.08
    POSITIVE LOGITS
    velopment
    0.14
    à¥įशन
    0.13
    ftar
    0.12
    ughter
    0.12
    quate
    0.12
    /DD
    0.11
    ï¿£ï½Ģ
    0.11
    apolis
    0.11
    estic
    0.10
    irable
    0.10
    Activations Density 0.193%

    No Known Activations