© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127698
    Prev
    Next
    INDEX
    Explanations

    concepts related to brain health and cognitive function

    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
    skin
    -0.07
    æŁľ
    -0.07
     Shelter
    -0.06
     пÑĢим
    -0.06
    à¥įथल
    -0.06
     skin
    -0.06
    ERV
    -0.06
    onation
    -0.06
    èĩ
    -0.06
    Skin
    -0.06
    POSITIVE LOGITS
     brain
    0.15
     Brain
    0.15
    Brain
    0.12
    brain
    0.12
     brains
    0.12
     hippoc
    0.10
    Brains
    0.10
    èĦij
    0.10
     memory
    0.10
     Memory
    0.10
    Activations Density 0.016%

    No Known Activations