© 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. 123256
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and associated establishments

    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
    007
    -0.06
    ettes
    -0.06
    ergy
    -0.05
     ASAP
    -0.05
    å»
    -0.05
    roph
    -0.05
    é§
    -0.05
    aims
    -0.05
    Answers
    -0.05
    pest
    -0.05
    POSITIVE LOGITS
     address
    0.12
    Address
    0.12
     Address
    0.12
    address
    0.12
     ADDRESS
    0.11
     adress
    0.11
    ADDRESS
    0.11
    åľ°åĿĢ
    0.10
     PO
    0.10
    .address
    0.10
    Activations Density 0.037%

    No Known Activations