© 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. 44777
    Prev
    Next
    INDEX
    Explanations

    in the production to context

    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
    EMPLARY
    -0.09
     RectTransform
    -0.08
    ripp
    -0.08
    ¶Į
    -0.08
    ìĸ¼
    -0.08
    .hl
    -0.08
    endi
    -0.07
     ãĢī
    -0.07
    ä¸Ģä¸ĭ
    -0.07
    /moment
    -0.07
    POSITIVE LOGITS
     these
    0.09
     said
    0.09
     männer
    0.09
    ursive
    0.08
    /hooks
    0.08
     your
    0.08
    -SA
    0.08
    oji
    0.08
     Herman
    0.08
     aforementioned
    0.08
    Activations Density 0.370%

    No Known Activations