© 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. 76735
    Prev
    Next
    INDEX
    Explanations

    references to literary works and authors, with a focus on specific elements like year, nationality, and distinctions

    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
    ¨¨
    -0.08
     Trafford
    -0.07
    ernote
    -0.07
    ToWorld
    -0.07
    ofday
    -0.06
    Animating
    -0.06
    ãĥĦ
    -0.06
    onta
    -0.06
    夫
    -0.06
    adolu
    -0.06
    POSITIVE LOGITS
     unless
    0.07
    ãĤ«ãĥĨãĤ´ãĥª
    0.07
    unless
    0.07
    )
    0.07
    ians
    0.06
     category
    0.06
    )|
    0.06
    Unless
    0.06
    614
    0.06
    nga
    0.06
    Activations Density 0.003%

    No Known Activations