© 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. 30555
    Prev
    Next
    INDEX
    Explanations

    what follows 'with', 'method', 'that', 'follow'

    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
     %[
    -0.10
    ï¿
    -0.08
    .osgi
    -0.08
    339
    -0.08
    fad
    -0.07
     navr
    -0.07
     sene
    -0.07
     meld
    -0.07
    ุà¸Ķà¸Ĺ
    -0.07
    Lorem
    -0.07
    POSITIVE LOGITS
    &apos
    0.09
    URLException
    0.09
     slightly
    0.08
    taj
    0.08
    PostalCodes
    0.08
    Intialized
    0.07
     kaldır
    0.07
     fuzzy
    0.07
    "default
    0.07
    à¸Ĺย
    0.07
    Activations Density 2.455%

    No Known Activations