© 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. 50944
    Prev
    Next
    INDEX
    Explanations

    programming instructions

    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
     titular
    -0.09
     carefully
    -0.09
    kaar
    -0.09
     ven
    -0.09
     correct
    -0.09
     Welcome
    -0.09
     reg
    -0.09
    iese
    -0.09
    ãĤ¢ãĥ³
    -0.08
    oce
    -0.08
    POSITIVE LOGITS
    aremos
    0.20
     lets
    0.19
    æĪij们
    0.18
     vamos
    0.18
     sake
    0.17
    å§ij
    0.17
     we
    0.17
     purposes
    0.17
     ours
    0.16
     shall
    0.16
    Activations Density 0.352%

    No Known Activations