© 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. 11323
    Prev
    Next
    INDEX
    Explanations

    biblical texts and concepts

    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
     Scripture
    -0.11
    _CF
    -0.10
    edi
    -0.10
    ontent
    -0.09
    agner
    -0.09
    anter
    -0.09
    IMA
    -0.09
    AXB
    -0.09
    ribbon
    -0.09
    abor
    -0.09
    POSITIVE LOGITS
    lical
    0.16
     passage
    0.12
     Belt
    0.12
     passages
    0.11
    gateway
    0.11
     Lands
    0.10
    ic
    0.10
    LS
    0.10
     fran
    0.09
     Concord
    0.09
    Activations Density 0.030%

    No Known Activations