© 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. 5068
    Prev
    Next
    INDEX
    Explanations

    numbers followed by countable parts

    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
     rims
    -0.10
     Woj
    -0.10
    issen
    -0.09
     Jab
    -0.09
    oby
    -0.09
    öl
    -0.08
    å®Ĺ
    -0.08
    adu
    -0.08
    393
    -0.08
     Numeric
    -0.08
    POSITIVE LOGITS
     teeth
    0.15
     fingers
    0.14
     vert
    0.12
     letters
    0.12
    digit
    0.11
     spokes
    0.11
     ribs
    0.11
     letter
    0.11
     component
    0.11
     Teeth
    0.11
    Activations Density 0.225%

    No Known Activations