© 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. 56577
    Prev
    Next
    INDEX
    Explanations

    methodology and method

    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
    ignment
    -0.12
    ipt
    -0.10
    uar
    -0.10
    åĪ¶åº¦
    -0.09
    atur
    -0.09
    ibly
    -0.09
    Ŀå§ĭ
    -0.09
    elo
    -0.09
    Ñĩа
    -0.09
     Cousins
    -0.09
    POSITIVE LOGITS
    ological
    0.25
    ical
    0.21
    论
    0.20
    ologies
    0.20
    ology
    0.19
    è«ĸ
    0.19
    ically
    0.17
    ologically
    0.17
    ë¡ł
    0.17
    (Method
    0.14
    Activations Density 0.035%

    No Known Activations