© 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. 60512
    Prev
    Next
    INDEX
    Explanations

    The followed by a noun

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

    the word "The" at the beginning of sentences or titles.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    nam
    -0.10
    ｿ
    -0.09
    most
    -0.09
    aviest
    -0.09
    Touches
    -0.09
    name
    -0.08
    okoj
    -0.08
    iest
    -0.08
    sec
    -0.08
    >NN
    -0.08
    POSITIVE LOGITS
    orem
    0.24
    aters
    0.22
    ater
    0.21
    oretical
    0.20
    atre
    0.19
    ories
    0.18
    orical
    0.17
    oret
    0.16
    odore
    0.15
    ft
    0.14
    Activations Density 0.111%

    No Known Activations