© 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. 60535
    Prev
    Next
    INDEX
    Explanations

    passive states and actions

    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
     wink
    -0.11
     smile
    -0.10
     smiles
    -0.10
     eyebrow
    -0.09
    å¾®ç¬ij
    -0.09
     Shock
    -0.09
    _logger
    -0.09
     Sin
    -0.09
    ibles
    -0.09
     smiled
    -0.09
    POSITIVE LOGITS
     heads
    0.25
     lowered
    0.21
     head
    0.20
     Heads
    0.18
     hang
    0.18
     lowering
    0.17
     bowed
    0.17
     aver
    0.15
    heads
    0.15
     avoid
    0.15
    Activations Density 0.020%

    No Known Activations