© 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. 38663
    Prev
    Next
    INDEX
    Explanations

    time periods measured in months

    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
     decade
    -0.22
     tháºŃp
    -0.11
     hourly
    -0.11
     winters
    -0.11
     summers
    -0.10
    hour
    -0.10
     decades
    -0.10
     McCl
    -0.10
     fortn
    -0.10
     quad
    -0.10
    POSITIVE LOGITS
     months
    0.46
     Months
    0.36
     meses
    0.32
    months
    0.31
    Months
    0.30
     меÑģÑıÑĨев
    0.29
     six
    0.23
     меÑģÑıÑĨа
    0.22
     mÄĽsÃŃců
    0.22
    ê°ľìĽĶ
    0.21
    Activations Density 0.119%

    No Known Activations