© 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. 85480
    Prev
    Next
    INDEX
    Explanations

    terms associated with passports and travel documentation

    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
    abouts
    -0.09
    à¹Ĩ
    -0.08
    erness
    -0.08
    Ùij
    -0.08
    öz
    -0.07
    ìĶ
    -0.06
    odia
    -0.06
    æº
    -0.06
    obsolete
    -0.06
     kli
    -0.06
    POSITIVE LOGITS
    folios
    0.08
    é¦Ĩ
    0.08
    館
    0.08
    ivated
    0.07
    ued
    0.07
    ry
    0.07
    ssi
    0.07
    è¢ĭ
    0.07
    TypeID
    0.06
     Iss
    0.06
    Activations Density 0.003%

    No Known Activations