© 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. 21409
    Prev
    Next
    INDEX
    Explanations

    ways to create or use

    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
     flere
    -0.10
    erver
    -0.10
    ëĿ¼ëıĦ
    -0.10
     several
    -0.09
    ữ
    -0.09
     nÄĽkteré
    -0.09
    onom
    -0.09
     некоÑĤоÑĢÑĭÑħ
    -0.09
    orna
    -0.08
     certain
    -0.08
    POSITIVE LOGITS
     depending
    0.24
     different
    0.21
     Depending
    0.18
    depending
    0.17
     diferentes
    0.16
     Different
    0.15
     various
    0.15
    different
    0.15
     varying
    0.15
    ä¸įåIJĮçļĦ
    0.15
    Activations Density 0.212%

    No Known Activations