© 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. 17101
    Prev
    Next
    INDEX
    Explanations

    leave the room

    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
    uen
    -0.09
    å»Ĭ
    -0.09
     ext
    -0.09
     multid
    -0.08
     auth
    -0.08
    ars
    -0.08
     Nile
    -0.08
    orex
    -0.08
     adj
    -0.08
     disguise
    -0.08
    POSITIVE LOGITS
     scene
    0.16
     room
    0.14
     premises
    0.13
    scene
    0.11
    çİ°åľº
    0.11
    åł´
    0.11
    Scene
    0.11
     Dodge
    0.10
    building
    0.10
     Room
    0.10
    Activations Density 0.010%

    No Known Activations