© 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. 18604
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical measurements and mappings

    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
    ennen
    -0.07
    sein
    -0.07
    jišť
    -0.06
    wner
    -0.06
    rica
    -0.06
     اÙĦÙħص
    -0.06
     pst
    -0.06
    oker
    -0.06
    vetica
    -0.06
     Raf
    -0.06
    POSITIVE LOGITS
    adecimal
    0.06
    (square
    0.06
     Pays
    0.06
    eldorf
    0.06
    277
    0.05
    ovice
    0.05
    ategori
    0.05
    onso
    0.05
    /qu
    0.05
     Quadr
    0.05
    Activations Density 0.008%

    No Known Activations