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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57631
    Prev
    Next
    INDEX
    Explanations

    stylistic elements and variations of the word "style."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yb
    -0.08
    leans
    -0.07
    alim
    -0.07
    ofday
    -0.07
    leston
    -0.07
    yor
    -0.07
    inem
    -0.07
    holding
    -0.07
    .scalablytyped
    -0.06
    lev
    -0.06
    POSITIVE LOGITS
    rex
    0.07
    nga
    0.07
    ater
    0.07
    uated
    0.07
    å¼ı
    0.06
    reate
    0.06
    ewise
    0.06
    ated
    0.06
    ning
    0.06
    agogue
    0.06
    Activations Density 0.007%

    No Known Activations