© 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. 25885
    Prev
    Next
    INDEX
    Explanations

    such followed by a noun

    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
    anko
    -0.11
    ï¸
    -0.10
    awan
    -0.10
    rtl
    -0.09
    RESP
    -0.08
    unks
    -0.08
    oded
    -0.08
     ï¼¼:
    -0.08
    gui
    -0.08
    件
    -0.08
    POSITIVE LOGITS
    itra
    0.17
    like
    0.16
     thing
    0.14
     kinds
    0.14
     kind
    0.13
     воÑĤ
    0.12
     things
    0.12
    ily
    0.12
    hle
    0.11
    -like
    0.11
    Activations Density 0.019%

    No Known Activations