© 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. 105237
    Prev
    Next
    INDEX
    Explanations

    references to public spaces or amenities

    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
    asha
    -0.06
    ph
    -0.06
    ολ
    -0.06
     MMI
    -0.06
     Roads
    -0.06
    ubic
    -0.06
    ENER
    -0.06
     Toll
    -0.06
     closure
    -0.05
    /sm
    -0.05
    POSITIVE LOGITS
    aname
    0.08
    ouns
    0.07
    æĸ½
    0.07
    undos
    0.07
    égor
    0.07
    /public
    0.06
    olith
    0.06
     "-//
    0.06
    -access
    0.06
    sterol
    0.06
    Activations Density 0.012%

    No Known Activations