© 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. 34537
    Prev
    Next
    INDEX
    Explanations

    for durations of time

    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
    иÑĢÑĥ
    -0.09
    figcaption
    -0.09
    ene
    -0.09
    inho
    -0.09
    elle
    -0.09
     thiá»ĥu
    -0.09
    kan
    -0.09
    ãģ°ãģĭãĤĬ
    -0.09
    é¾
    -0.08
     lifetime
    -0.08
    POSITIVE LOGITS
     quite
    0.20
     weeks
    0.16
    ages
    0.16
     months
    0.15
     years
    0.15
     ages
    0.14
     so
    0.14
    AGES
    0.13
    aging
    0.12
    age
    0.12
    Activations Density 0.034%

    No Known Activations