© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43
    Prev
    Next
    INDEX
    Explanations

    evaluating behavior

    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
    çIJĨ
    -0.09
     çIJĨ
    -0.09
     seeming
    -0.08
    prs
    -0.08
    hill
    -0.08
     motiv
    -0.08
    etti
    -0.08
     Vance
    -0.08
     Hogan
    -0.08
    uki
    -0.07
    POSITIVE LOGITS
     behavior
    0.12
     Behavior
    0.10
     evaluate
    0.10
     behaviour
    0.10
     next
    0.10
     Äijánh
    0.10
     here
    0.09
    readcr
    0.09
    è¯Ħä»·
    0.09
     Evaluate
    0.09
    Activations Density 0.010%

    No Known Activations