© 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. 107542
    Prev
    Next
    INDEX
    Explanations

    mentions of local dining or eating locations

    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
    egg
    -0.08
    erap
    -0.07
     PureComponent
    -0.07
    idl
    -0.07
    .geom
    -0.07
    ÂŃi
    -0.07
    çĺ
    -0.07
    avax
    -0.07
    ̣
    -0.07
    .findIndex
    -0.06
    POSITIVE LOGITS
     tables
    0.07
     restaurant
    0.07
     restaurants
    0.07
    ennie
    0.07
    vik
    0.07
     ram
    0.06
    oir
    0.06
     table
    0.06
     Tables
    0.06
     sit
    0.06
    Activations Density 0.017%

    No Known Activations