© 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. 31977
    Prev
    Next
    INDEX
    Explanations

    garnished with cherry or to sprinkle

    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
    ziel
    -0.11
     backing
    -0.10
    Hosting
    -0.10
    ARB
    -0.09
     decl
    -0.09
    asons
    -0.09
    oad
    -0.09
    _soft
    -0.08
    heim
    -0.08
     Belle
    -0.08
    POSITIVE LOGITS
     dr
    0.20
     garn
    0.19
     Garn
    0.16
     top
    0.15
     Spr
    0.13
     additional
    0.12
     edible
    0.12
     serve
    0.12
     丶
    0.12
     dust
    0.11
    Activations Density 0.022%

    No Known Activations