© 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. 38927
    Prev
    Next
    INDEX
    Explanations

    references to Britain and its characteristics or context

    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
    conde
    -0.07
    arel
    -0.07
    æĬŀ
    -0.07
     Hutchinson
    -0.07
    ery
    -0.07
    ORIES
    -0.07
    (es
    -0.07
    eras
    -0.07
    leh
    -0.07
    ailable
    -0.06
    POSITIVE LOGITS
     Isles
    0.11
     Columbia
    0.07
    tingham
    0.07
    /E
    0.07
    ness
    0.07
    /world
    0.07
     Colum
    0.07
    shire
    0.07
    umbs
    0.07
    nal
    0.06
    Activations Density 0.017%

    No Known Activations