© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    this introduces a concept

    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
    ä¹ħ
    -0.09
    _configs
    -0.09
    oggler
    -0.09
    undy
    -0.08
    atto
    -0.08
    aryl
    -0.08
    _RST
    -0.08
     Geile
    -0.08
    olumn
    -0.08
    å¢
    -0.08
    POSITIVE LOGITS
     particular
    0.19
     latter
    0.16
     type
    0.16
     sort
    0.16
     kind
    0.16
    /th
    0.13
     entire
    0.13
     approach
    0.12
    æķ´ä¸ª
    0.11
     whole
    0.11
    Activations Density 0.038%

    No Known Activations