© 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. 34522
    Prev
    Next
    INDEX
    Explanations

    world descriptions

    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
    ToWorld
    -0.11
    aurus
    -0.11
    furt
    -0.10
    ulle
    -0.10
     Worldwide
    -0.10
    usra
    -0.09
    emez
    -0.09
    lâm
    -0.09
     worldwide
    -0.09
    /watch
    -0.09
    POSITIVE LOGITS
    liness
    0.25
    views
    0.17
    lier
    0.17
    -class
    0.15
    lings
    0.14
    ometers
    0.12
    -wide
    0.12
    scale
    0.12
    -view
    0.12
    building
    0.12
    Activations Density 0.043%

    No Known Activations