© 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. 63473
    Prev
    Next
    INDEX
    Explanations

    body parts in physical states

    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
    vil
    -0.14
    iko
    -0.10
    /generated
    -0.10
     Gale
    -0.09
    alach
    -0.09
     Franco
    -0.09
    IsActive
    -0.09
    .scalablytyped
    -0.09
     onto
    -0.08
    apsulation
    -0.08
    POSITIVE LOGITS
     open
    0.21
     closed
    0.14
    open
    0.14
     spread
    0.13
     turned
    0.13
     açık
    0.12
     offen
    0.12
     drawn
    0.12
     down
    0.11
     Spread
    0.10
    Activations Density 0.082%

    No Known Activations