© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    recommend specific, combining these, before any actions

    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
     Ler
    -0.10
     Hydra
    -0.09
    asic
    -0.09
     ent
    -0.08
     precios
    -0.08
    YG
    -0.08
    دÙĨ
    -0.08
     ê
    -0.08
     corruption
    -0.08
     Curl
    -0.08
    POSITIVE LOGITS
     any
    0.16
     new
    0.16
    ä»»ä½ķ
    0.14
    new
    0.12
     self
    0.11
     neue
    0.11
    æĸ°çļĦ
    0.11
     especially
    0.11
     unfamiliar
    0.11
     ANY
    0.11
    Activations Density 0.029%

    No Known Activations