© 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. 63664
    Prev
    Next
    INDEX
    Explanations

    at the same time

    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
     Bek
    -0.10
     all
    -0.10
    tle
    -0.10
     пÑĢиÑĩ
    -0.09
    otti
    -0.09
    atum
    -0.09
    ubits
    -0.09
     तब
    -0.09
    oki
    -0.08
    essler
    -0.08
    POSITIVE LOGITS
     once
    0.37
    once
    0.27
     Once
    0.27
    Once
    0.25
     fois
    0.21
    _once
    0.21
     einmal
    0.20
    ä¸Ģ度
    0.20
     Ùħرة
    0.19
     vez
    0.18
    Activations Density 0.015%

    No Known Activations