© 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. 118729
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific landmarks

    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
    annel
    -0.07
    еÑĢин
    -0.07
    /etc
    -0.06
    FW
    -0.06
    raphics
    -0.06
    ogl
    -0.06
    inki
    -0.06
    ERG
    -0.06
    umbo
    -0.06
    ést
    -0.06
    POSITIVE LOGITS
     viewed
    0.07
     NONINFRINGEMENT
    0.07
    ;amp
    0.07
    ċ
    0.06
    detail
    0.06
    شتÙĩ
    0.06
     Caucasian
    0.06
    blr
    0.06
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.06
     Detail
    0.06
    Activations Density 0.004%

    No Known Activations