© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22324
    Prev
    Next
    INDEX
    Explanations

    concrete objects and concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    common nouns referring to everyday concrete entities—especially animals, objects/clothing, foods, bodily substances, simple shapes, and common events.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ÂĢÂĢ
    -0.12
    ¶Į
    -0.10
    įng
    -0.10
    EMPLARY
    -0.09
    _________________\n\n
    -0.09
    ¡´
    -0.09
    ĮĴ
    -0.09
    ¿ÃĤ
    -0.09
    ¡ng
    -0.09
    ķãĤĵ
    -0.09
    POSITIVE LOGITS
     itself
    0.09
     suce
    0.08
     proport
    0.08
     Grove
    0.08
    irs
    0.08
     obviously
    0.08
    0.08
     Fork
    0.08
     Conrad
    0.07
    rote
    0.07
    Activations Density 1.102%

    No Known Activations