© 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. 34693
    Prev
    Next
    INDEX
    Explanations

    appears to be

    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
    kaar
    -0.10
    rais
    -0.09
    :::
    -0.09
    åĪ°çļĦ
    -0.09
     pant
    -0.09
    åĪ°äºĨ
    -0.09
    ToUpper
    -0.09
     (
    -0.09
     appearing
    -0.08
    iare
    -0.08
    POSITIVE LOGITS
    antly
    0.18
     být
    0.17
     byÄĩ
    0.16
     essere
    0.13
     être
    0.12
     бÑĭÑĤÑĮ
    0.11
     to
    0.11
     vara
    0.11
     бÑĥÑĤи
    0.11
     να
    0.11
    Activations Density 0.019%

    No Known Activations