© 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. 21167
    Prev
    Next
    INDEX
    Explanations

    is said / is due / is believed

    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
     previously
    -0.12
     recently
    -0.11
     initially
    -0.11
    /is
    -0.10
     stub
    -0.09
    emos
    -0.09
     originally
    -0.09
     Present
    -0.09
     present
    -0.09
     Gä
    -0.09
    POSITIVE LOGITS
    /w
    0.23
     now
    0.18
    now
    0.13
     ÑĤепеÑĢÑĮ
    0.13
     бÑĭло
    0.12
    otope
    0.12
     اÙĦØ¢ÙĨ
    0.12
    rael
    0.11
     believed
    0.11
     continuing
    0.11
    Activations Density 0.201%

    No Known Activations