© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 60310
    Prev
    Next
    INDEX
    Explanations

    is followed by a capitalized word

    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
    IsNull
    -0.11
     isConnected
    -0.10
    ãģĦ
    -0.09
    ton
    -0.09
    ãģªãģĦ
    -0.09
    orny
    -0.09
    oki
    -0.09
     Malik
    -0.09
    ulis
    -0.09
    IsActive
    -0.09
    POSITIVE LOGITS
    atty
    0.16
    lands
    0.13
    subclass
    0.12
    odate
    0.12
    olation
    0.11
    rael
    0.11
    olate
    0.11
    omorphic
    0.10
    .EqualTo
    0.10
    veç
    0.10
    Activations Density 0.043%

    No Known Activations