© 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. 27212
    Prev
    Next
    INDEX
    Explanations

    modeling random, hierarchical, various

    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
     meas
    -0.09
    ous
    -0.08
    656
    -0.08
    pedia
    -0.08
     nest
    -0.08
    /effects
    -0.08
     overthrow
    -0.08
     Russo
    -0.08
    oola
    -0.08
    511
    -0.08
    POSITIVE LOGITS
     situations
    0.18
     things
    0.12
     complicated
    0.11
     systems
    0.11
     anything
    0.10
     situation
    0.10
     scenarios
    0.10
     many
    0.10
     any
    0.10
     lists
    0.10
    Activations Density 0.180%

    No Known Activations