© 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. 23735
    Prev
    Next
    INDEX
    Explanations

    learning and recognition

    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
     thr
    -0.10
    828
    -0.09
     convolution
    -0.09
    Validate
    -0.09
    ?(:
    -0.08
    æ³Ĭ
    -0.08
     Cyril
    -0.08
     BUS
    -0.08
    767
    -0.08
     Monte
    -0.08
    POSITIVE LOGITS
     mapping
    0.14
     output
    0.13
     input
    0.13
    learn
    0.12
     representation
    0.12
     outputs
    0.12
    æĭŁ
    0.12
     nonlinear
    0.12
     inputs
    0.11
    representation
    0.11
    Activations Density 0.079%

    No Known Activations