© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41351
    Prev
    Next
    INDEX
    Explanations

    more specific, higher level

    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
     actively
    -0.11
     wider
    -0.10
     Mehr
    -0.10
     non
    -0.10
    elia
    -0.10
    ÐIJÑĢÑħÑĸв
    -0.09
    YNAMIC
    -0.09
     Non
    -0.09
    agi
    -0.09
     stag
    -0.09
    POSITIVE LOGITS
     focused
    0.24
     laser
    0.22
     Laser
    0.19
    focused
    0.18
    ä¸ĵ
    0.17
     focus
    0.17
    Focused
    0.17
    ocused
    0.17
     narrow
    0.16
     foc
    0.16
    Activations Density 0.112%

    No Known Activations