© 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. 46544
    Prev
    Next
    INDEX
    Explanations

    breeding of breeds

    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
     genus
    -0.14
     genetically
    -0.10
     Monkey
    -0.10
    olis
    -0.10
     Shepard
    -0.10
     Genre
    -0.09
     pups
    -0.09
     calves
    -0.09
    Migration
    -0.09
     Puppy
    -0.09
    POSITIVE LOGITS
    bre
    0.18
     Bre
    0.18
     crosses
    0.17
    -bre
    0.17
     recess
    0.16
    Bre
    0.16
     bre
    0.16
     studs
    0.16
     traits
    0.15
     crossings
    0.15
    Activations Density 0.076%

    No Known Activations