© 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. 27963
    Prev
    Next
    INDEX
    Explanations

    I instruct, ask, or tell

    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
    зна
    -0.09
    ihad
    -0.08
     nháºŃn
    -0.08
    idth
    -0.08
     presum
    -0.08
    )prepare
    -0.08
     slim
    -0.08
     CAUSED
    -0.08
    iba
    -0.08
     spit
    -0.08
    POSITIVE LOGITS
     ask
    0.13
     asking
    0.13
     asks
    0.12
     tell
    0.12
     command
    0.11
     asked
    0.10
     ëªħ
    0.10
     give
    0.10
    åij½ä»¤
    0.10
     tells
    0.10
    Activations Density 0.145%

    No Known Activations