© 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. 26170
    Prev
    Next
    INDEX
    Explanations

    javascript code and syntax

    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
    aleza
    -0.10
     competit
    -0.10
     Braun
    -0.09
     Lux
    -0.09
    uar
    -0.09
     Cran
    -0.09
    ivan
    -0.09
    ___
    -0.08
    Ticks
    -0.08
    ButtonModule
    -0.08
    POSITIVE LOGITS
     const
    0.18
     useEffect
    0.18
     return
    0.16
    return
    0.13
     render
    0.13
     handle
    0.13
     componentDidMount
    0.12
    \treturn
    0.12
    const
    0.11
     Const
    0.11
    Activations Density 0.025%

    No Known Activations