Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 78332
    Prev
    Next
    INDEX
    Explanations

    references to the act of closing or opening eyes and other related actions

    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
    iser
    -0.07
    osg
    -0.07
    elan
    -0.07
    Blob
    -0.07
    obot
    -0.07
    anchise
    -0.07
    aggio
    -0.07
    ñana
    -0.06
    à¥Ģल
    -0.06
    à¤Ĥà¤ļ
    -0.06
    POSITIVE LOGITS
    ukes
    0.06
    ULE
    0.06
    -fontawesome
    0.06
    gap
    0.06
    ãĤ¦ãĤ¹
    0.06
    UZ
    0.06
    376
    0.06
    TV
    0.06
    .gdx
    0.06
     اÙĦÙ쨱
    0.06
    Activations Density 0.005%

    No Known Activations