© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    diagnosis and diagnostics

    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
    allen
    -0.12
    swick
    -0.10
    ted
    -0.09
    ocities
    -0.09
    ulence
    -0.09
    iness
    -0.09
    Normalization
    -0.09
    sik
    -0.09
    rey
    -0.09
    çek
    -0.08
    POSITIVE LOGITS
    óst
    0.15
    itian
    0.11
    osing
    0.11
    ure
    0.11
    æĸŃ
    0.10
    icians
    0.10
    IEL
    0.10
    uer
    0.09
    atically
    0.09
    atik
    0.09
    Activations Density 0.026%

    No Known Activations