© 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. 42327
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations and features

    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
    qm
    -0.07
    csi
    -0.07
     rodin
    -0.07
    enson
    -0.07
    á»ĥ
    -0.06
    940
    -0.06
    ủ
    -0.06
    Ùģات
    -0.06
    Europe
    -0.06
    944
    -0.06
    POSITIVE LOGITS
    inois
    0.07
    AVED
    0.07
     Samar
    0.06
    /filepath
    0.06
    	Copyright
    0.06
    searchModel
    0.06
     Barcl
    0.06
    bare
    0.06
     Yug
    0.06
    prus
    0.06
    Activations Density 0.217%

    No Known Activations