© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14770
    Prev
    Next
    INDEX
    Explanations

    news and commentary coverage

    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
     Newspaper
    -0.12
     newspaper
    -0.12
    revision
    -0.10
     sadd
    -0.09
     press
    -0.09
     newspapers
    -0.09
     mentioning
    -0.08
    kt
    -0.08
    immel
    -0.08
    896
    -0.08
    POSITIVE LOGITS
     coverage
    0.24
     reporting
    0.18
     covers
    0.18
     Coverage
    0.17
    coverage
    0.17
     Covers
    0.17
     cover
    0.16
    æĬ¥éģĵ
    0.16
     covering
    0.16
     оÑģвеÑī
    0.16
    Activations Density 0.115%

    No Known Activations