© 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. 34910
    Prev
    Next
    INDEX
    Explanations

    sur- prefix and related words

    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
    eration
    -0.09
     Contrib
    -0.09
    ÅŁk
    -0.09
    ãģĬãĤĬ
    -0.09
     Glover
    -0.08
     ped
    -0.08
     enforcement
    -0.08
    rang
    -0.08
    ebb
    -0.08
     Bye
    -0.08
    POSITIVE LOGITS
    acing
    0.19
    icial
    0.16
     surf
    0.13
    ACING
    0.12
    aced
    0.12
    casting
    0.11
    iness
    0.11
    prene
    0.11
    boards
    0.11
    board
    0.10
    Activations Density 0.004%

    No Known Activations