© 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. 31692
    Prev
    Next
    INDEX
    Explanations

    information outside context

    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
     bất
    -0.10
    ê¸Ķ
    -0.09
     any
    -0.09
    inner
    -0.09
     ç¬
    -0.09
     tall
    -0.09
    'gc
    -0.09
     incon
    -0.09
    paque
    -0.08
    idor
    -0.08
    POSITIVE LOGITS
     outside
    0.25
     beyond
    0.22
     unless
    0.19
    outside
    0.17
     Outside
    0.17
    以å¤ĸ
    0.16
    Outside
    0.15
    unless
    0.15
     ngoÃłi
    0.15
    eyond
    0.15
    Activations Density 0.133%

    No Known Activations