© 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. 98501
    Prev
    Next
    INDEX
    Explanations

    the presence of geographical or regional terms and their context in the text

    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
    aus
    -0.07
    earer
    -0.07
    atürk
    -0.07
    éri
    -0.07
    yna
    -0.07
    prene
    -0.07
    eous
    -0.06
    riad
    -0.06
    ÏĦ
    -0.06
    insk
    -0.06
    POSITIVE LOGITS
     Speech
    0.07
     pageTitle
    0.06
    ãģıãģł
    0.06
    askell
    0.06
     Düz
    0.06
     nos
    0.06
    uzey
    0.06
    Speech
    0.06
     Sharing
    0.06
    αιν
    0.06
    Activations Density 0.014%

    No Known Activations