© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 53248
    Prev
    Next
    INDEX
    Explanations

    safe for use, may be harmful

    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
    Negative Logits
    utex
    -0.11
     Puppy
    -0.10
     Cre
    -0.10
     kitten
    -0.09
     Sinclair
    -0.09
     puppies
    -0.09
    evi
    -0.09
     hunger
    -0.09
     kittens
    -0.09
     Sands
    -0.09
    POSITIVE LOGITS
     treats
    0.16
     owners
    0.15
     treat
    0.13
     human
    0.13
     Owners
    0.12
     safe
    0.12
     humans
    0.12
    labs
    0.12
    ileo
    0.12
     pet
    0.11
    Activations Density 0.044%

    No Known Activations