© 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. 24197
    Prev
    Next
    INDEX
    Explanations

    for the essence | and aligning

    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
     incarn
    -0.11
     supernatural
    -0.10
    grav
    -0.10
     Kov
    -0.09
     widow
    -0.09
     cov
    -0.09
     Heavenly
    -0.09
    Occurred
    -0.09
     Floral
    -0.09
    robat
    -0.09
    POSITIVE LOGITS
    528
    0.14
     Source
    0.14
     Sanat
    0.13
     expansion
    0.13
    Source
    0.13
     Ga
    0.13
    Expansion
    0.12
     masculine
    0.12
     frequency
    0.12
     allowance
    0.12
    Activations Density 0.059%

    No Known Activations