© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125741
    Prev
    Next
    INDEX
    Explanations

    references to proximity and closeness in relationships or situations

    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
    dem
    -0.08
    jak
    -0.07
    flash
    -0.07
    orsch
    -0.07
    odelist
    -0.07
    ìĸij
    -0.06
    uede
    -0.06
    ificial
    -0.06
    vertime
    -0.06
    FLASH
    -0.06
    POSITIVE LOGITS
     close
    0.10
     clos
    0.10
     proximity
    0.10
    /close
    0.10
    close
    0.10
    -close
    0.09
    .close
    0.09
    (close
    0.09
     Close
    0.09
     CLOSE
    0.09
    Activations Density 0.022%

    No Known Activations