© 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. 28754
    Prev
    Next
    INDEX
    Explanations

    in science and engineering

    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
     Orbit
    -0.10
     Moreno
    -0.10
    ingo
    -0.10
    inesis
    -0.09
    ync
    -0.09
     parallel
    -0.09
     Alejandro
    -0.09
     è¾
    -0.08
    ίθ
    -0.08
     rejuven
    -0.08
    POSITIVE LOGITS
     practical
    0.13
    fields
    0.13
     daily
    0.12
    å·¥ç¨ĭ
    0.12
     Branch
    0.12
     fields
    0.12
     applications
    0.11
     engineering
    0.11
    daily
    0.11
     problem
    0.11
    Activations Density 0.065%

    No Known Activations