© 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. 36764
    Prev
    Next
    INDEX
    Explanations

    and keep 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
     cage
    -0.10
     Cage
    -0.10
     tavs
    -0.10
     cages
    -0.09
     AVR
    -0.08
     outlet
    -0.08
     rost
    -0.08
     karak
    -0.08
    ampling
    -0.08
     Mitch
    -0.08
    POSITIVE LOGITS
     Passive
    0.16
     fen
    0.14
     thermal
    0.14
     energy
    0.14
     dra
    0.14
     passive
    0.14
     gl
    0.13
     ins
    0.13
     solar
    0.13
    irt
    0.13
    Activations Density 0.026%

    No Known Activations