© 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. 9-LLAMASCOPE-RES-131K
    11. 96333
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and properties related to dimensions and solutions in complex systems

    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
    iny
    -0.08
    UCT
    -0.07
    mdat
    -0.07
    orman
    -0.07
    uct
    -0.07
    quo
    -0.07
    æ´¥
    -0.07
    tright
    -0.06
    ection
    -0.06
    rete
    -0.06
    POSITIVE LOGITS
    ugin
    0.06
    å³
    0.06
     hend
    0.06
    367
    0.06
     Yog
    0.06
    231
    0.05
    Ùı
    0.05
     Haw
    0.05
    ç±
    0.05
     Getty
    0.05
    Activations Density 0.072%

    No Known Activations