© 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. 108869
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and keys (as in key areas or keynotes)

    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
    pac
    -0.07
    st
    -0.06
    jee
    -0.06
    aca
    -0.06
    iset
    -0.06
    anos
    -0.06
    phere
    -0.06
    sta
    -0.06
    ulary
    -0.06
    out
    -0.06
    POSITIVE LOGITS
    ãģİ
    0.09
    /key
    0.08
    hole
    0.08
    =key
    0.08
     ingredient
    0.08
    edi
    0.08
    ingredient
    0.08
    ekil
    0.08
    zer
    0.08
    ser
    0.08
    Activations Density 0.011%

    No Known Activations