© 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. 13664
    Prev
    Next
    INDEX
    Explanations

    accumulation or aggregate

    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
     Improved
    -0.09
    ennes
    -0.09
    ieg
    -0.09
     Garr
    -0.09
     expended
    -0.09
    uen
    -0.08
    åĬĥ
    -0.08
    agi
    -0.08
     Sunder
    -0.08
     actively
    -0.08
    POSITIVE LOGITS
    积
    0.43
     накоп
    0.37
    ç´¯
    0.36
    accum
    0.36
     accumulation
    0.35
     acum
    0.34
    ç©į
    0.33
     accum
    0.31
     Accum
    0.31
     birik
    0.30
    Activations Density 0.121%

    No Known Activations