© 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. 5475
    Prev
    Next
    INDEX
    Explanations

    baking soda, powder, ingredients

    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
    ëį°
    -0.26
    ÂŃing
    -0.14
    ability
    -0.13
    sh
    -0.13
    sWith
    -0.12
    ings
    -0.12
    sc
    -0.12
    sen
    -0.11
    ê°ĢìļĶ
    -0.11
    scan
    -0.11
    POSITIVE LOGITS
    redients
    0.24
    gg
    0.21
    redient
    0.18
    uez
    0.15
    ham
    0.14
    HAM
    0.14
    ton
    0.14
    /loading
    0.14
    /testing
    0.13
    REDIENT
    0.13
    Activations Density 0.113%

    No Known Activations