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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44423
    Prev
    Next
    INDEX
    Explanations

    press arrow keys

    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
     Kare
    -0.10
    keyboard
    -0.09
    lider
    -0.09
    _KEYBOARD
    -0.09
     Nex
    -0.09
     PSU
    -0.09
    abb
    -0.09
     Siege
    -0.09
    Keyboard
    -0.09
    æĿ
    -0.08
    POSITIVE LOGITS
     Enter
    0.16
     space
    0.15
     Space
    0.15
     escape
    0.14
     SDLK
    0.14
    Enter
    0.13
    .space
    0.13
     Escape
    0.13
     enter
    0.12
     Esc
    0.12
    Activations Density 0.014%

    No Known Activations