© 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. 58456
    Prev
    Next
    INDEX
    Explanations

    "four" or "A4"

    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
     Five
    -0.12
     five
    -0.12
     quint
    -0.12
     triple
    -0.11
    ABCDE
    -0.11
    isti
    -0.10
    Five
    -0.10
     threesome
    -0.10
     Triple
    -0.10
    tring
    -0.09
    POSITIVE LOGITS
     åĽĽ
    0.23
     fourth
    0.22
     four
    0.22
     quart
    0.22
     Four
    0.22
     FOUR
    0.22
    åĽĽ
    0.21
     fours
    0.21
    Four
    0.20
    Fourth
    0.20
    Activations Density 0.188%

    No Known Activations