© 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. 27
    Prev
    Next
    INDEX
    Explanations

    involves or means

    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
    าà¸
    -0.08
     Rav
    -0.08
    awei
    -0.08
    koli
    -0.08
     rá»ĵi
    -0.08
    cheduler
    -0.08
    inclusive
    -0.08
     поба
    -0.07
    uien
    -0.07
    lsi
    -0.07
    POSITIVE LOGITS
     involves
    0.13
    æ¶ī
    0.12
     involve
    0.12
     include
    0.11
    implify
    0.10
     involved
    0.10
    ÃĹ\n\n
    0.10
     includes
    0.10
     requires
    0.10
    iglia
    0.09
    Activations Density 0.011%

    No Known Activations