© 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. 55933
    Prev
    Next
    INDEX
    Explanations

    let's imagine, explore, journey, enter

    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
    ãģ«ãģĭ
    -0.10
     distant
    -0.09
    eyse
    -0.09
     pense
    -0.09
    óÅĤ
    -0.09
    ieten
    -0.09
    jal
    -0.08
     undo
    -0.08
     exh
    -0.08
    ï¼ıï¼ı
    -0.08
    POSITIVE LOGITS
     enters
    0.26
     enter
    0.26
    è¿Ľåħ¥
    0.25
     journey
    0.24
    enter
    0.23
     entered
    0.23
     into
    0.23
     entering
    0.22
    -enter
    0.21
    Enter
    0.21
    Activations Density 0.179%

    No Known Activations