© 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. 17483
    Prev
    Next
    INDEX
    Explanations

    combined with

    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
     wit
    -0.18
     Wit
    -0.13
    wit
    -0.11
     Prelude
    -0.09
     Farrell
    -0.09
    ÑģоÑĤ
    -0.09
     Kear
    -0.09
     Ku
    -0.09
    icamente
    -0.09
     Rag
    -0.09
    POSITIVE LOGITS
     with
    0.23
     vỼi
    0.21
     dengan
    0.19
    with
    0.17
     avec
    0.16
    gether
    0.15
     withString
    0.15
     together
    0.15
    \twith
    0.11
    itech
    0.11
    Activations Density 0.031%

    No Known Activations