© 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. 40707
    Prev
    Next
    INDEX
    Explanations

    named after

    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
    çĽijåIJ¬é¡µéĿ¢
    -0.11
    874
    -0.09
    ANE
    -0.09
    umn
    -0.09
    letcher
    -0.09
     subsequently
    -0.09
    umin
    -0.08
     Extr
    -0.08
     longitudinal
    -0.08
     later
    -0.08
    POSITIVE LOGITS
     after
    0.51
    after
    0.41
     efter
    0.32
    -after
    0.32
     поÑģле
    0.32
    _after
    0.31
     dopo
    0.30
    .after
    0.29
    After
    0.29
    (after
    0.29
    Activations Density 0.058%

    No Known Activations