© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16620
    Prev
    Next
    INDEX
    Explanations

    references to the word "this" or "this book."

    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
     majority
    -0.07
    acht
    -0.06
     poste
    -0.06
     ëĦ¤ìĿ´íĬ¸
    -0.06
    ace
    -0.06
     statement
    -0.06
    Ø®ÙĪØ§ÙĨ
    -0.06
    ↵↵
    -0.06
    .â̦↵↵
    -0.06
    uh
    -0.06
    POSITIVE LOGITS
    abouts
    0.07
    ä½ľèĢħ
    0.07
    主人
    0.07
     Realt
    0.06
    lags
    0.06
    egal
    0.06
    ichni
    0.06
    öst
    0.06
    ategory
    0.06
    )>>
    0.06
    Activations Density 0.005%

    No Known Activations