© 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. 27416
    Prev
    Next
    INDEX
    Explanations

    tight deadline, held in a place, visual component

    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
     increasingly
    -0.10
    elong
    -0.10
     probably
    -0.10
    alchemy
    -0.09
     slightly
    -0.09
    \-
    -0.09
    å¤ļå°ij
    -0.09
     twice
    -0.09
     Harr
    -0.09
    sembl
    -0.09
    POSITIVE LOGITS
     lots
    0.21
     particularly
    0.21
     Lots
    0.16
     lot
    0.16
    Lots
    0.15
    lots
    0.15
     hodnÄĽ
    0.15
    particularly
    0.15
    å¾Īå¤ļ
    0.15
    大éĩı
    0.14
    Activations Density 0.117%

    No Known Activations