© 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
    5. 50-RESID-POST-GF
    7. 38744
    Prev
    Next
    INDEX
    Explanations

    map layout with businesses

    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
     atmos
    -0.10
     techn
    -0.09
     engines
    -0.09
    PILE
    -0.09
     frames
    -0.09
     stated
    -0.09
    Window
    -0.08
     sidel
    -0.08
    paralle
    -0.08
     parallel
    -0.08
    POSITIVE LOGITS
     layout
    0.44
    layout
    0.33
     Layout
    0.32
     layouts
    0.28
    Layout
    0.28
    _layout
    0.28
    -layout
    0.28
    .layout
    0.27
    \tlayout
    0.26
     map
    0.25
    Activations Density 0.141%

    No Known Activations