© 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. 42829
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating spatial relationships or locations

    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
    phia
    -0.08
    folk
    -0.08
    elas
    -0.07
    senal
    -0.07
    orate
    -0.07
    unner
    -0.07
    \Context
    -0.07
    .fhir
    -0.07
    /trunk
    -0.07
    ÙĦÙĥتر
    -0.07
    POSITIVE LOGITS
     one
    0.08
     the
    0.08
     his
    0.07
    appa
    0.07
     Dut
    0.06
     our
    0.06
     a
    0.06
    arty
    0.06
    our
    0.06
     an
    0.06
    Activations Density 0.051%

    No Known Activations