© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44741
    Prev
    Next
    INDEX
    Explanations

    common cause

    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
    hya
    -0.11
     Meredith
    -0.09
     Greg
    -0.09
    intern
    -0.09
    æŃ
    -0.09
    undan
    -0.09
    æŁĦ
    -0.09
    anos
    -0.09
    oble
    -0.09
    anie
    -0.09
    POSITIVE LOGITS
     driver
    0.18
    Driver
    0.15
     Driver
    0.14
     rel
    0.14
     drivers
    0.14
    driver
    0.14
    AML
    0.13
    -driver
    0.13
     Fusion
    0.12
    fusion
    0.12
    Activations Density 0.059%

    No Known Activations