© 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. 63846
    Prev
    Next
    INDEX
    Explanations

    `Ok` function is a function

    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
     ties
    -0.10
    ãģ¬
    -0.09
    rote
    -0.09
     Yuan
    -0.08
     TRUE
    -0.08
     true
    -0.08
     literal
    -0.08
     Reign
    -0.08
    .toggle
    -0.08
     SYN
    -0.08
    POSITIVE LOGITS
     mon
    0.24
     Mon
    0.16
     Kle
    0.15
     >>=
    0.14
    lift
    0.14
    -mon
    0.14
    mon
    0.14
     мон
    0.13
     sequencing
    0.13
     Lens
    0.12
    Activations Density 0.021%

    No Known Activations