© 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. 2048
    Prev
    Next
    INDEX
    Explanations

    behavior or functionality

    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
     Lambert
    -0.10
    lesh
    -0.09
    unn
    -0.09
    ignon
    -0.09
    variables
    -0.09
    .za
    -0.08
    aters
    -0.08
    à¸Ńะ
    -0.08
     Gret
    -0.08
     PyErr
    -0.08
    POSITIVE LOGITS
     behavior
    0.40
    è¡Į为
    0.34
     behaviour
    0.33
     Behavior
    0.32
     functionality
    0.32
     повед
    0.30
    behavior
    0.27
    Behavior
    0.25
    _behavior
    0.25
     Behaviour
    0.22
    Activations Density 0.129%

    No Known Activations