© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 108830
    Prev
    Next
    INDEX
    Explanations

    elements related to geographic or historical context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    -0.06
     (
    -0.06
    x
    -0.06
    OA
    -0.06
     –
    -0.06
    #w
    -0.06
    irs
    -0.06
     Gio
    -0.06
    esch
    -0.06
     equip
    -0.05
    POSITIVE LOGITS
    à¥ĩà¤Ĥ↵
    0.09
    *)↵
    0.09
    à¹ī↵
    0.08
    č↵
    0.08
    надлеж
    0.07
    ा↵
    0.07
    nock
    0.07
    enties
    0.07
     âĸ²
    0.07
    ï¼ī↵
    0.07
    Activations Density 0.095%

    No Known Activations