© 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. 40651
    Prev
    Next
    INDEX
    Explanations

    epic fantasy prose style

    np_acts-logits-general · gemini-2.5-flash-lite

    references to stylistic or literary writing qualities, particularly formal, elevated, or antiquated language.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     slang
    -0.10
    adero
    -0.10
     reign
    -0.10
     rep
    -0.09
     autobi
    -0.09
     subt
    -0.09
    chine
    -0.09
     adorable
    -0.09
    abbr
    -0.09
    ault
    -0.09
    POSITIVE LOGITS
     dramatic
    0.28
     grand
    0.18
     Dram
    0.18
     dramatically
    0.18
     drama
    0.18
    DRAM
    0.17
     dram
    0.15
     epic
    0.14
     romantic
    0.14
    åºĦ
    0.14
    Activations Density 0.184%

    No Known Activations