© 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. 34225
    Prev
    Next
    INDEX
    Explanations

    `<|text start|>` or `<start>`

    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
     bare
    -0.09
     ***!\n
    -0.09
    /misc
    -0.08
     unus
    -0.08
    âĶĺ
    -0.08
     bait
    -0.08
    út
    -0.08
     sur
    -0.08
     worm
    -0.08
    lox
    -0.08
    POSITIVE LOGITS
    ><
    0.10
     wes
    0.09
    ACKET
    0.09
     Cham
    0.09
     hybrid
    0.09
     Wes
    0.09
     Blond
    0.09
     Hybrid
    0.08
    åµ
    0.08
    ored
    0.08
    Activations Density 0.013%

    No Known Activations