© 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. 84451
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to user interface functionality

    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
    ÏĦα
    -0.07
     neglig
    -0.07
     oku
    -0.06
    ãĥ©ãĤ¤
    -0.06
    met
    -0.06
    wayne
    -0.06
    боÑĤ
    -0.06
    azzi
    -0.06
    jo
    -0.06
    grass
    -0.06
    POSITIVE LOGITS
     Gian
    0.07
    .MixedReality
    0.06
    alers
    0.06
    compressed
    0.06
     Dak
    0.06
     Madd
    0.05
     cave
    0.05
    .names
    0.05
    uant
    0.05
     Lowest
    0.05
    Activations Density 0.001%

    No Known Activations