© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    mechanism definition and purpose

    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
    tainment
    -0.11
    /activity
    -0.09
    erah
    -0.09
    ãĥ¥
    -0.09
    üzel
    -0.09
     liá»ĩu
    -0.09
    weis
    -0.09
    IRC
    -0.09
    ULAR
    -0.09
    ifying
    -0.09
    POSITIVE LOGITS
    isms
    0.17
    ically
    0.15
    eer
    0.13
    anism
    0.12
     mechanism
    0.12
     mechanisms
    0.12
     Mechan
    0.12
    atically
    0.11
    ally
    0.11
    isto
    0.10
    Activations Density 0.020%

    No Known Activations