© 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. 42591
    Prev
    Next
    INDEX
    Explanations

    asking which one

    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
    âħ¥
    -0.10
    ĮĴ
    -0.09
    unction
    -0.09
    outine
    -0.09
     mere
    -0.09
     amp
    -0.09
    ipop
    -0.09
    issan
    -0.09
    imal
    -0.09
    '])?
    -0.09
    POSITIVE LOGITS
     parts
    0.19
    parts
    0.16
     specific
    0.16
     part
    0.16
    åħ·ä½ĵ
    0.15
     конкÑĢеÑĤ
    0.14
     sentences
    0.14
     ones
    0.14
     specifically
    0.13
    (s
    0.13
    Activations Density 0.013%

    No Known Activations