© 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. 17037
    Prev
    Next
    INDEX
    Explanations

    first

    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
    ivr
    -0.09
    990
    -0.09
    âij¡
    -0.09
    enne
    -0.08
    935
    -0.08
     preceded
    -0.08
    pch
    -0.08
    unma
    -0.08
    otr
    -0.08
    BorderStyle
    -0.08
    POSITIVE LOGITS
    第ä¸Ģ
    0.48
     first
    0.42
     첫
    0.41
     第ä¸Ģ
    0.38
     erste
    0.37
     eerste
    0.37
     пеÑĢвого
    0.36
     pierws
    0.35
    first
    0.35
     ersten
    0.35
    Activations Density 0.232%

    No Known Activations