© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33396
    Prev
    Next
    INDEX
    Explanations

    mist

    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
    izzard
    -0.11
    erge
    -0.10
    ENCY
    -0.10
    erp
    -0.10
    ignment
    -0.10
    arkan
    -0.10
    iento
    -0.10
    /WebAPI
    -0.10
    ETERS
    -0.10
    stown
    -0.10
    POSITIVE LOGITS
    ubishi
    0.20
    reatment
    0.17
    resses
    0.15
    ral
    0.15
    ellaneous
    0.14
    y
    0.14
    akes
    0.14
     mist
    0.13
    ery
    0.13
    emean
    0.12
    Activations Density 0.021%

    No Known Activations