© 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. 61566
    Prev
    Next
    INDEX
    Explanations

    information acquisition and transaction verbs

    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
    alles
    -0.09
    ä¹ĭä¸Ģ
    -0.09
    æĺ¯ä¸Ģ个
    -0.09
     several
    -0.09
    óż
    -0.09
    /stdc
    -0.08
    /raw
    -0.08
    件
    -0.08
    uzz
    -0.08
    rious
    -0.08
    POSITIVE LOGITS
    /access
    0.11
     stuff
    0.10
    ä¸ľè¥¿
    0.09
     things
    0.09
    /view
    0.09
    ullo
    0.09
    æĤ
    0.09
    umu
    0.09
     goods
    0.09
     ÂŃ
    0.08
    Activations Density 0.160%

    No Known Activations