© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 35460
    Prev
    Next
    INDEX
    Explanations

    involves setting, proactive, addressing

    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
    /gif
    -0.09
    phin
    -0.09
     prelim
    -0.09
     Rossi
    -0.08
     gate
    -0.08
    _dur
    -0.08
    abras
    -0.08
     dere
    -0.08
     Perc
    -0.08
    浩
    -0.08
    POSITIVE LOGITS
     react
    0.19
    react
    0.19
     reaction
    0.19
    /react
    0.18
     Reaction
    0.18
    -react
    0.17
    åıįåºĶ
    0.17
     pro
    0.16
    React
    0.16
    Reaction
    0.16
    Activations Density 0.045%

    No Known Activations