© 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. 105264
    Prev
    Next
    INDEX
    Explanations

    references to specific regions or cities related to events and demographics

    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
    ly
    -0.09
    ered
    -0.09
    liness
    -0.09
    ÑģÑĮ
    -0.08
    lie
    -0.08
    LY
    -0.08
    lies
    -0.08
    edly
    -0.08
    nt
    -0.07
    mente
    -0.07
    POSITIVE LOGITS
    ulously
    0.10
    dden
    0.09
    ilitating
    0.09
    ãĤ©
    0.08
    istory
    0.08
    iran
    0.07
    éra
    0.07
    imized
    0.07
    clinical
    0.07
    ов
    0.07
    Activations Density 0.022%

    No Known Activations