© 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. 61690
    Prev
    Next
    INDEX
    Explanations

    naming, pricing, and scheduling concepts

    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
    ëį°
    -0.21
    /cop
    -0.14
    ability
    -0.11
    çĿĢ
    -0.10
    swith
    -0.10
    /Foundation
    -0.10
    ersh
    -0.09
    (s
    -0.09
    spr
    -0.09
     Herc
    -0.09
    POSITIVE LOGITS
    redients
    0.18
    gg
    0.13
    /testing
    0.13
    uez
    0.12
     done
    0.12
    redient
    0.12
    HAM
    0.11
    enuity
    0.11
    ham
    0.11
    ton
    0.11
    Activations Density 0.128%

    No Known Activations