© 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. 78129
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific processes and materials

    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
     conectar
    -0.06
    awe
    -0.06
    orer
    -0.06
    LineWidth
    -0.06
     Synd
    -0.06
    лÑĥб
    -0.06
    owler
    -0.06
    kul
    -0.06
     synd
    -0.06
     tapped
    -0.06
    POSITIVE LOGITS
     Motion
    0.08
     motion
    0.08
    .motion
    0.08
     Swimming
    0.07
    -flag
    0.07
    ÃĹ↵↵
    0.07
    -motion
    0.07
    Powered
    0.07
     Swim
    0.07
    ĶĦ
    0.07
    Activations Density 0.005%

    No Known Activations