© 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. 1958
    Prev
    Next
    INDEX
    Explanations

    can + action verb

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    readcr
    -0.10
    ubar
    -0.10
    ibase
    -0.09
    ewire
    -0.09
    swire
    -0.09
    SEE
    -0.09
    ledon
    -0.09
    -Ray
    -0.09
     kür
    -0.09
    ellen
    -0.08
    POSITIVE LOGITS
     try
    0.24
     Try
    0.16
    try
    0.15
    Try
    0.15
    \ttry
    0.15
    ’;t
    0.14
     simply
    0.14
     instead
    0.14
    't
    0.14
     also
    0.14
    Activations Density 0.039%

    No Known Activations