© 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. 15-LLAMASCOPE-RES-131K
    11. 85987
    Prev
    Next
    INDEX
    Explanations

    references to small groups or minorities within larger contexts

    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
    ']!='
    -0.07
    entifier
    -0.07
     salope
    -0.07
    éĭ
    -0.07
    amar
    -0.07
    asio
    -0.07
    _IPV
    -0.07
    806
    -0.06
    agenta
    -0.06
    berger
    -0.06
    POSITIVE LOGITS
     (<
    0.09
    ãģªãģĮãĤī
    0.08
     cases
    0.07
     (~
    0.07
     exceptions
    0.07
    ãģ¾ãĤĮ
    0.06
    å£
    0.06
    edor
    0.06
     Cases
    0.06
     Exceptions
    0.06
    Activations Density 0.023%

    No Known Activations