© 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. 51821
    Prev
    Next
    INDEX
    Explanations

    channels, biopsy, dots, file, around, bird, sitting, wind, procedure

    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
    .instant
    -0.09
    .coroutines
    -0.09
    hatt
    -0.09
    IRT
    -0.08
    kening
    -0.08
    ï¼ı/
    -0.08
    IDEO
    -0.08
     sprav
    -0.08
    pNet
    -0.08
    AffineTransform
    -0.08
    POSITIVE LOGITS
     ad
    0.09
    mania
    0.09
    ган
    0.08
    quisa
    0.08
     unf
    0.08
    ugo
    0.08
    isy
    0.08
    dro
    0.08
     Continue
    0.08
     Gregg
    0.08
    Activations Density 0.885%

    No Known Activations