© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    sales progress or representative

    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
    oulos
    -0.12
    avigation
    -0.10
    peq
    -0.10
    -shell
    -0.09
     pon
    -0.09
    \n\n
    -0.09
     chip
    -0.09
     coron
    -0.09
     shell
    -0.09
    Checksum
    -0.09
    POSITIVE LOGITS
     sales
    0.46
     Sales
    0.42
    Sales
    0.37
    sales
    0.33
    -sales
    0.32
    .sales
    0.29
     salesman
    0.27
    éĶĢåĶ®
    0.27
     selling
    0.25
    _sales
    0.25
    Activations Density 0.144%

    No Known Activations