© 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. 41063
    Prev
    Next
    INDEX
    Explanations

    beginning the start 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
     amateurs
    -0.10
     amateur
    -0.09
     çĻ
    -0.09
    jis
    -0.09
    /end
    -0.09
    çĶ²
    -0.09
     оÑĩеÑĢед
    -0.09
     poslednÃŃch
    -0.08
     midterm
    -0.08
     walkthrough
    -0.08
    POSITIVE LOGITS
     initial
    0.41
     Initial
    0.33
     first
    0.32
    Initial
    0.31
    initial
    0.30
    åĪĿ
    0.29
    first
    0.28
     åĪĿ
    0.25
    _initial
    0.25
     첫
    0.25
    Activations Density 0.404%

    No Known Activations