© 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. 37635
    Prev
    Next
    INDEX
    Explanations

    confined to following instructions

    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
    667
    -0.10
     Gab
    -0.10
    기ëıĦ
    -0.09
     гÑĥб
    -0.09
    aub
    -0.09
    ancel
    -0.08
    aben
    -0.08
    è
    -0.08
    ishi
    -0.08
     Tab
    -0.08
    POSITIVE LOGITS
     limited
    0.44
     restricted
    0.37
    limited
    0.36
     Stick
    0.33
     stick
    0.33
     confined
    0.33
    éĻIJå®ļ
    0.32
     limit
    0.32
     Limited
    0.30
    Stick
    0.30
    Activations Density 0.223%

    No Known Activations