© 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. 38219
    Prev
    Next
    INDEX
    Explanations

    inquiries and expressions of interest related to real estate

    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
    ulous
    -0.06
    enance
    -0.06
     Bridges
    -0.06
    aire
    -0.06
     Robertson
    -0.06
     Draft
    -0.05
    iks
    -0.05
     æµ
    -0.05
     Dup
    -0.05
     sunk
    -0.05
    POSITIVE LOGITS
    rát
    0.07
    ubar
    0.07
     Claw
    0.07
    alet
    0.07
    dera
    0.07
    stery
    0.07
     claw
    0.06
     Handlers
    0.06
    utral
    0.06
    oes
    0.06
    Activations Density 0.001%

    No Known Activations