© 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. 61058
    Prev
    Next
    INDEX
    Explanations

    step out, move to, receding

    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
    antar
    -0.10
     ç¿
    -0.10
    ë¬
    -0.09
    fty
    -0.09
    estre
    -0.09
    orney
    -0.08
     deserted
    -0.08
     Stre
    -0.08
    iseum
    -0.08
    isplay
    -0.08
    POSITIVE LOGITS
     step
    0.39
     retreat
    0.35
     stepped
    0.35
     Step
    0.32
    step
    0.31
     back
    0.31
     backing
    0.31
     stepping
    0.30
    -step
    0.30
     backed
    0.29
    Activations Density 0.046%

    No Known Activations