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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18094
    Prev
    Next
    INDEX
    Explanations

    concepts related to organizational structure and design

    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
    ELS
    -0.07
     uniform
    -0.07
    nech
    -0.06
     rop
    -0.06
    /stats
    -0.06
     sketch
    -0.06
     moz
    -0.06
     paramet
    -0.06
    391
    -0.06
     moth
    -0.06
    POSITIVE LOGITS
    PERT
    0.08
    formance
    0.07
    egen
    0.07
    ikip
    0.07
    ildo
    0.07
    isté
    0.07
    oki
    0.06
    оген
    0.06
     Clamp
    0.06
    ought
    0.06
    Activations Density 0.003%

    No Known Activations