© 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. 56714
    Prev
    Next
    INDEX
    Explanations

    questions starting with how can

    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
    EMPLARY
    -0.10
    Å¡ak
    -0.10
    IRQ
    -0.10
    ến
    -0.09
    elay
    -0.09
    .Formatter
    -0.09
    lehem
    -0.08
    961
    -0.08
    ureau
    -0.08
    dür
    -0.08
    POSITIVE LOGITS
    ’;t
    0.14
    /w
    0.13
    /do
    0.13
    æĪij
    0.13
     we
    0.12
    't
    0.12
     tôi
    0.12
    oes
    0.11
     someone
    0.10
    onical
    0.10
    Activations Density 0.077%

    No Known Activations