© 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. 5508
    Prev
    Next
    INDEX
    Explanations

    the + specific noun

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

    the word "The" at the beginning of assistant responses or explanatory sentences.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @yooniel31
    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
     newest
    -0.11
     Nug
    -0.10
     hint
    -0.10
    稿
    -0.09
    hint
    -0.09
     pat
    -0.08
     specifically
    -0.08
    df
    -0.08
     wording
    -0.08
     Map
    -0.08
    POSITIVE LOGITS
     following
    0.15
     given
    0.15
    orem
    0.15
     Following
    0.14
    ater
    0.14
    atre
    0.13
    odore
    0.12
    oretical
    0.12
     Given
    0.12
     above
    0.12
    Activations Density 0.089%

    No Known Activations