© 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. 24593
    Prev
    Next
    INDEX
    Explanations

    teaching and tutorials

    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
    LLL
    -0.10
    âĢŀTo
    -0.09
     instructional
    -0.09
     Mature
    -0.09
    abinet
    -0.09
    AGMA
    -0.09
    âĢŀP
    -0.09
     Monroe
    -0.09
    typeid
    -0.09
    âĢŀJ
    -0.08
    POSITIVE LOGITS
     Hands
    0.12
     Manning
    0.12
     topics
    0.12
     scre
    0.12
     hands
    0.12
     Bolt
    0.10
     Ud
    0.10
     Ramp
    0.10
     Programming
    0.10
     teaching
    0.10
    Activations Density 0.249%

    No Known Activations