© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 40808
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases

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

    relational function words, especially prepositions and conjunctions that link entities or indicate relationships such as cause, association, purpose, or direction.

    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
    ¶Į
    -0.15
    çĹħ
    -0.12
    ekim
    -0.10
    iddi
    -0.10
    ¦æĥħ
    -0.10
     Infect
    -0.10
    èĹ¥
    -0.10
    ĮĴ
    -0.09
    lsa
    -0.09
    çĹĩ
    -0.09
    POSITIVE LOGITS
     tel
    0.11
     ket
    0.10
     Eh
    0.10
     brain
    0.10
     Ket
    0.09
     Calc
    0.09
     Kund
    0.09
     fasc
    0.09
     calc
    0.09
     COVID
    0.09
    Activations Density 0.403%

    No Known Activations