© 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. 33150
    Prev
    Next
    INDEX
    Explanations

    this + noun specification

    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
    ¶Į
    -0.09
    ÂĢÂĢ
    -0.09
    кÑĥÑģ
    -0.09
    obox
    -0.09
    ãģĵãģ¡ãĤī
    -0.08
    çļĦæĺ¯
    -0.08
     بس
    -0.08
    <|begin_of_text|>
    -0.08
    ·»
    -0.08
    acle
    -0.08
    POSITIVE LOGITS
    /th
    0.26
     particular
    0.21
     kind
    0.15
    że
    0.14
    ìłĢ
    0.13
     type
    0.13
    (th
    0.13
    kind
    0.12
     particul
    0.11
     PARTICULAR
    0.11
    Activations Density 0.119%

    No Known Activations