© 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 EvalsExportsAPI 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. 16380
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and their relevance in discussions

    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
    ìķ¼
    -0.10
     hence
    -0.09
     Hence
    -0.09
     holistic
    -0.09
    off
    -0.08
    appen
    -0.08
     harsh
    -0.07
    amm
    -0.07
    oner
    -0.07
    IPH
    -0.07
    POSITIVE LOGITS
    ERSHEY
    0.11
    iday
    0.11
    /software
    0.10
    sworth
    0.09
    izons
    0.09
    forth
    0.08
    RowAtIndexPath
    0.08
     sapi
    0.08
    essian
    0.08
    uckle
    0.08
    Activations Density 0.753%

    No Known Activations