© 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. 9-LLAMASCOPE-RES-131K
    11. 94729
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases associated with inquiry or research activities

    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
    pcl
    -0.07
    oland
    -0.07
    ollen
    -0.07
    _PROTO
    -0.06
     eoq
    -0.06
     weiber
    -0.06
    ENOMEM
    -0.06
    óst
    -0.06
    ultan
    -0.06
    hma
    -0.06
    POSITIVE LOGITS
     Rub
    0.07
     rub
    0.06
     Spit
    0.06
     sho
    0.05
     res
    0.05
     Dix
    0.05
    оло
    0.05
    aled
    0.05
    113
    0.05
    aph
    0.05
    Activations Density 0.001%

    No Known Activations