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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5263
    Prev
    Next
    INDEX
    Explanations

    descriptions of emotional and aesthetic experiences

    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
    launcher
    -0.06
    strom
    -0.06
    оÑģоб
    -0.06
    chu
    -0.05
    byname
    -0.05
    èĹ
    -0.05
    оÑĢÑĸ
    -0.05
    bid
    -0.05
    ernote
    -0.05
    гал
    -0.05
    POSITIVE LOGITS
     scene
    0.31
     scenes
    0.27
     Scene
    0.25
     sight
    0.25
    scene
    0.24
    Scene
    0.23
     Scenes
    0.21
     sights
    0.21
    _scene
    0.20
    scenes
    0.20
    Activations Density 0.079%

    No Known Activations