© 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. 28348
    Prev
    Next
    INDEX
    Explanations

    published/written/won numerous/many

    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
    ä¸Ģç§į
    -0.10
    zee
    -0.09
     Certain
    -0.08
    ponde
    -0.08
    /from
    -0.08
     ANY
    -0.08
    AMPL
    -0.08
    979
    -0.08
     blink
    -0.08
    UAL
    -0.08
    POSITIVE LOGITS
     numerous
    0.39
     several
    0.36
     many
    0.28
     countless
    0.24
     zahl
    0.23
     Several
    0.22
     scores
    0.21
     Numerous
    0.21
    numer
    0.21
    许å¤ļ
    0.21
    Activations Density 0.104%

    No Known Activations