© 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. 44679
    Prev
    Next
    INDEX
    Explanations

    video that, have the

    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
     ï½°
    -0.11
    _Tis
    -0.10
     меÑĤалли
    -0.10
    togroup
    -0.09
    isContained
    -0.09
     fitte
    -0.09
    chandle
    -0.09
     appearances
    -0.09
    _Lean
    -0.09
    ----------</
    -0.09
    POSITIVE LOGITS
     task
    0.20
     topic
    0.19
     project
    0.16
     scenario
    0.16
     story
    0.16
     event
    0.15
    ä»»åĬ¡
    0.15
    é¢ĺ
    0.15
    task
    0.14
     episode
    0.14
    Activations Density 1.885%

    No Known Activations