© 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. 25244
    Prev
    Next
    INDEX
    Explanations

    query continuations

    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
    Opens
    -0.10
    renom
    -0.09
    onto
    -0.09
     vej
    -0.08
    vation
    -0.08
     Bale
    -0.08
    IPP
    -0.08
     <!--[
    -0.08
    UPDATE
    -0.08
    emy
    -0.08
    POSITIVE LOGITS
    /Dk
    0.10
     Wade
    0.08
    ILING
    0.08
    åīĤ
    0.08
    imei
    0.08
    -END
    0.08
    รà¸ģ
    0.08
    ÅĻád
    0.08
    æ§
    0.08
     inex
    0.08
    Activations Density 0.007%

    No Known Activations