© 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. 28501
    Prev
    Next
    INDEX
    Explanations

    concepts related to complexity and the emergence of life

    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
    æħ
    -0.07
    stal
    -0.06
    azu
    -0.06
     Bone
    -0.06
     Hort
    -0.06
     geographic
    -0.06
    .component
    -0.06
     bone
    -0.06
     puck
    -0.06
     fiscal
    -0.06
    POSITIVE LOGITS
    umo
    0.09
    okane
    0.08
    umpt
    0.08
     networks
    0.08
     Bates
    0.08
    ÐIJÑĢÑħÑĸв
    0.08
    PROTO
    0.07
    unce
    0.07
    loops
    0.07
    utow
    0.07
    Activations Density 0.012%

    No Known Activations