© 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. 42003
    Prev
    Next
    INDEX
    Explanations

    virtual assistants created by characters

    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
     evac
    -0.09
    å¥ī
    -0.09
     slogan
    -0.09
     бÑĥк
    -0.09
    -CP
    -0.08
     slogans
    -0.08
     Publication
    -0.08
    enko
    -0.08
     instrumental
    -0.08
     voyeur
    -0.08
    POSITIVE LOGITS
     fiction
    0.24
     movies
    0.22
     movie
    0.19
    -fiction
    0.19
     popular
    0.17
     media
    0.17
    çĶµå½±
    0.16
     Movies
    0.16
     Hollywood
    0.16
     fictional
    0.16
    Activations Density 0.207%

    No Known Activations