© 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. 149
    Prev
    Next
    INDEX
    Explanations

    dialog box interface

    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
    бол
    -0.10
     Lond
    -0.09
    >*</
    -0.09
     Tooltip
    -0.08
    -tooltip
    -0.08
     Barker
    -0.08
    lom
    -0.08
     cul
    -0.08
     Wales
    -0.08
    inel
    -0.08
    POSITIVE LOGITS
     appear
    0.11
    edList
    0.10
     dock
    0.10
    ula
    0.10
    -style
    0.10
     interface
    0.10
    ¾ç¤º
    0.10
    ocz
    0.10
     titled
    0.10
    asan
    0.09
    Activations Density 0.086%

    No Known Activations