© 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. 26851
    Prev
    Next
    INDEX
    Explanations

    references to job opportunities and real estate context

    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
    cision
    -0.07
    enko
    -0.07
    metatable
    -0.06
    ãĤĵãģ©
    -0.06
    stringstream
    -0.06
    rome
    -0.06
    PT
    -0.06
    ech
    -0.06
    ruc
    -0.06
    defgroup
    -0.06
    POSITIVE LOGITS
     interest
    0.12
     Interest
    0.11
    Interest
    0.10
     interesse
    0.09
    interest
    0.09
     interests
    0.08
    _interest
    0.08
     interes
    0.08
     concern
    0.08
    -interest
    0.07
    Activations Density 0.006%

    No Known Activations