© 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. 38489
    Prev
    Next
    INDEX
    Explanations

    geographic references and demographic data related to economic conditions

    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
    ¼åIJĪ
    -0.07
     Wayback
    -0.06
    nev
    -0.06
     controvers
    -0.06
    wart
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    ghi
    -0.06
    rypton
    -0.06
    inou
    -0.06
    -cols
    -0.06
    POSITIVE LOGITS
     reporting
    0.07
    /photo
    0.07
     except
    0.06
     ngoại
    0.06
    é¤
    0.06
    諸
    0.06
    ührung
    0.06
     Rest
    0.06
    Ïĥκε
    0.06
    -important
    0.06
    Activations Density 0.025%

    No Known Activations