© 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. 43731
    Prev
    Next
    INDEX
    Explanations

    codice, codigo, code

    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
    aycast
    -0.11
    thood
    -0.10
    ASCADE
    -0.10
    indows
    -0.10
    ŀæĢ§
    -0.10
    atures
    -0.10
    lÃ¼ÄŁ
    -0.09
     dab
    -0.09
    etwork
    -0.09
    ogue
    -0.09
    POSITIVE LOGITS
    ice
    0.14
    ding
    0.14
    ex
    0.14
    igos
    0.14
    pend
    0.14
    ded
    0.12
    s
    0.12
    ling
    0.12
    cks
    0.12
    екÑģ
    0.12
    Activations Density 0.017%

    No Known Activations