© 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. 80513
    Prev
    Next
    INDEX
    Explanations

    references to locations and institutions in Vermont

    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
     Dallas
    -0.13
    Dallas
    -0.11
     Chicago
    -0.11
     Texas
    -0.11
     Seattle
    -0.10
    Chicago
    -0.09
     Kansas
    -0.09
    Texas
    -0.09
     Atlanta
    -0.09
     Wichita
    -0.08
    POSITIVE LOGITS
     Vermont
    0.17
     Burlington
    0.09
    VT
    0.09
     NH
    0.09
    NH
    0.09
     Rhode
    0.08
    802
    0.08
     Norwich
    0.08
     Maine
    0.08
     Newfoundland
    0.08
    Activations Density 0.053%

    No Known Activations