© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 49103
    Prev
    Next
    INDEX
    Explanations

    advanced techniques and designs

    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
     Herrera
    -0.10
    exampleInput
    -0.09
     magn
    -0.09
    adesh
    -0.09
    丶
    -0.09
    FI
    -0.08
    uda
    -0.08
    elerine
    -0.08
    ucci
    -0.08
     Goldberg
    -0.08
    POSITIVE LOGITS
     techniques
    0.15
     technology
    0.13
     capabilities
    0.13
     technologies
    0.12
     Techniques
    0.11
    ãĢģé«ĺ
    0.11
    /high
    0.10
     features
    0.10
     facilities
    0.10
     concepts
    0.10
    Activations Density 0.081%

    No Known Activations