© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44136
    Prev
    Next
    INDEX
    Explanations

    numbered list items and symbols

    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
    AMPL
    -0.09
     Lager
    -0.08
    ¦
    -0.08
     Hedge
    -0.08
    atto
    -0.08
     trie
    -0.08
    ÐĤ
    -0.08
     Gesture
    -0.08
     notion
    -0.08
     ¦
    -0.08
    POSITIVE LOGITS
    :
    0.10
     labyrinth
    0.09
    ãĢĬ
    0.09
    >\<^
    0.09
    annies
    0.09
     consect
    0.08
    éré
    0.08
     API
    0.08
     beh
    0.08
    XR
    0.08
    Activations Density 0.016%

    No Known Activations