© 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. 5196
    Prev
    Next
    INDEX
    Explanations

    words starting with 'pr'

    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
    /print
    -0.11
    sworth
    -0.10
     пÑĢип
    -0.10
    ashtra
    -0.10
     cricket
    -0.09
     prayer
    -0.09
    aneous
    -0.09
     trai
    -0.09
    ï¸ı
    -0.09
     primitive
    -0.09
    POSITIVE LOGITS
    (PR
    0.16
    γμα
    0.13
    CESS
    0.12
    eworthy
    0.12
    à¸ı
    0.11
    mary
    0.11
    formance
    0.11
    ordial
    0.10
    MARY
    0.10
    fung
    0.10
    Activations Density 0.058%

    No Known Activations