© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43862
    Prev
    Next
    INDEX
    Explanations

    simply a/an or rather a/an

    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
    ＿＿
    -0.09
    ä¸Ģ人
    -0.08
    ä¿Ĺ
    -0.08
    _globals
    -0.08
    æľīä¸Ģ
    -0.07
    è¿Ļç§į
    -0.07
    ihn
    -0.07
    aÅŁa
    -0.07
     Anast
    -0.07
    inel
    -0.07
    POSITIVE LOGITS
     an
    0.26
     a
    0.22
     eine
    0.18
     something
    0.17
    an
    0.15
     een
    0.15
     another
    0.15
    a
    0.15
     part
    0.13
     evidence
    0.13
    Activations Density 0.186%

    No Known Activations