© 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. 46423
    Prev
    Next
    INDEX
    Explanations

    cannot wait or looking forward

    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
    reh
    -0.09
    aty
    -0.09
    ollo
    -0.09
     Rah
    -0.09
     Feast
    -0.08
    Impossible
    -0.08
    ETF
    -0.08
    cta
    -0.08
     Tent
    -0.08
    DeltaTime
    -0.08
    POSITIVE LOGITS
     wait
    0.36
    wait
    0.26
     Wait
    0.24
    Wait
    0.23
     cannot
    0.22
     WAIT
    0.22
     waits
    0.21
    .wait
    0.21
     Cannot
    0.21
     Cant
    0.21
    Activations Density 0.015%

    No Known Activations