© 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. 31350
    Prev
    Next
    INDEX
    Explanations

    alarm clock, drop-down menu, Milky Way galaxy, Seine River, dialog box, curveball, Scotch whisky

    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
     marvel
    -0.09
     sod
    -0.09
    esModule
    -0.08
    ivr
    -0.08
    acs
    -0.08
     Fahrenheit
    -0.08
    ospace
    -0.08
    edenÃŃ
    -0.08
    ings
    -0.08
     صÙĦÙī
    -0.08
    POSITIVE LOGITS
     Pradesh
    0.13
    ฯ
    0.12
    501
    0.10
    иÑĩа
    0.09
    _helpers
    0.08
    erializer
    0.08
    .gdx
    0.08
     guitar
    0.08
    ulta
    0.08
     обол
    0.08
    Activations Density 0.282%

    No Known Activations