© 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. 9737
    Prev
    Next
    INDEX
    Explanations

    to prioritize, respect, help

    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
    arkin
    -0.11
     loos
    -0.10
    æħ
    -0.10
     æħ
    -0.09
    acro
    -0.09
     Philipp
    -0.09
     Comfort
    -0.08
     replaces
    -0.08
    defgroup
    -0.08
    awan
    -0.08
    POSITIVE LOGITS
    èħ¾
    0.19
     free
    0.17
     spare
    0.15
     freed
    0.15
    ocus
    0.14
     fre
    0.14
    _focus
    0.14
     focus
    0.13
    éģ¿
    0.13
    é¨
    0.13
    Activations Density 0.102%

    No Known Activations