© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 105798
    Prev
    Next
    INDEX
    Explanations

    geographic names and terms associated with countries and regions

    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
    ecd
    -0.07
    >{!!
    -0.07
    ersh
    -0.07
    sted
    -0.07
    á»ĵi
    -0.07
    æĮ¥
    -0.07
     Eag
    -0.06
     Lafayette
    -0.06
    oba
    -0.06
     Refer
    -0.06
    POSITIVE LOGITS
    Bell
    0.08
    ells
    0.07
    ellt
    0.07
     Bell
    0.07
     Ellison
    0.07
     bell
    0.07
    ällt
    0.07
    hell
    0.07
    ell
    0.07
    elle
    0.06
    Activations Density 0.008%

    No Known Activations