© 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. 39111
    Prev
    Next
    INDEX
    Explanations

    geographic locations and nationality or language identifiers

    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
    pedia
    -0.07
    CORD
    -0.07
    ÏģοÏį
    -0.07
    occer
    -0.06
    afi
    -0.06
    úb
    -0.06
    wing
    -0.06
    važ
    -0.06
    iswa
    -0.06
    edia
    -0.06
    POSITIVE LOGITS
     Aires
    0.07
    708
    0.07
     appearing
    0.07
    itan
    0.06
     national
    0.06
     Marino
    0.06
     McCartney
    0.06
    662
    0.06
    Vien
    0.06
    Appearance
    0.06
    Activations Density 0.003%

    No Known Activations