© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18674
    Prev
    Next
    INDEX
    Explanations

    noun followed by a verb or connector

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

    clause connectors and hedging/modal constructions characteristic of formal, expository descriptions.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
    ÐIJÑĢÑħÑĸв
    -0.11
    }elseif
    -0.09
    exampleInput
    -0.08
     Hüs
    -0.08
    etine
    -0.08
     %[
    -0.08
    ÐĴÑĤ
    -0.08
     salopes
    -0.08
     Erotische
    -0.08
    isContained
    -0.08
    POSITIVE LOGITS
    &apos
    0.09
     necess
    0.08
    op
    0.08
     accompl
    0.08
    ov
    0.07
    .Yellow
    0.07
    SetValue
    0.07
     dicks
    0.07
         \n\n
    0.07
    toISOString
    0.07
    Activations Density 2.908%

    No Known Activations