© 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. 36030
    Prev
    Next
    INDEX
    Explanations

    irreducible representations of dimension

    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
    igram
    -0.11
     radix
    -0.10
     ann
    -0.09
    Trait
    -0.09
    issa
    -0.09
     Epic
    -0.09
     Pierce
    -0.09
     DB
    -0.09
     Fant
    -0.09
     Ferm
    -0.09
    POSITIVE LOGITS
     irre
    0.13
     Rac
    0.12
     IR
    0.11
    icos
    0.11
     Cox
    0.11
     SO
    0.10
     symmetry
    0.10
     tet
    0.10
     group
    0.10
     molecular
    0.10
    Activations Density 0.021%

    No Known Activations