© 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. 57969
    Prev
    Next
    INDEX
    Explanations

    outlining steps

    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
     ostr
    -0.10
    cales
    -0.09
    ike
    -0.09
    794
    -0.09
    537
    -0.08
     traction
    -0.08
    wik
    -0.08
     rein
    -0.08
    etype
    -0.08
    è°
    -0.08
    POSITIVE LOGITS
     steps
    0.53
     Steps
    0.44
    steps
    0.42
    æŃ¥
    0.40
     step
    0.40
    Steps
    0.39
    _steps
    0.33
     ÑĪаг
    0.31
    step
    0.30
    -step
    0.30
    Activations Density 0.220%

    No Known Activations