© 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. 23792
    Prev
    Next
    INDEX
    Explanations

    concluding blocks and sections

    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
    agus
    -0.10
    empo
    -0.10
    à¹Ģหล
    -0.09
    ocratic
    -0.09
     Luna
    -0.09
    -0.09
    645
    -0.09
     Mon
    -0.09
    ãĤº
    -0.09
    adro
    -0.09
    POSITIVE LOGITS
    orse
    0.14
    ImageContext
    0.14
    orses
    0.13
    owed
    0.11
    ereco
    0.11
    ereço
    0.10
    :initComponents
    0.10
    itchens
    0.10
    ef
    0.10
    game
    0.09
    Activations Density 0.024%

    No Known Activations