© 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. 104546
    Prev
    Next
    INDEX
    Explanations

    mentions of office furniture and related working conditions

    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
    impse
    -0.07
    ÑĥÑĢи
    -0.07
    gles
    -0.07
    ulaire
    -0.07
    avian
    -0.06
    rien
    -0.06
    ubo
    -0.06
    EditingController
    -0.06
    ëĿ½
    -0.06
    steen
    -0.06
    POSITIVE LOGITS
     sed
    0.10
     sitting
    0.09
     Sitting
    0.09
     office
    0.08
     desk
    0.08
     Ñģид
    0.07
     posture
    0.07
     Sed
    0.07
     hour
    0.07
     seated
    0.07
    Activations Density 0.010%

    No Known Activations