© 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. 18597
    Prev
    Next
    INDEX
    Explanations

    phrases discussing impacts and effects of various factors on subjects, particularly in relation to health and environmental issues

    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
    ãģĿãģĹãģ¦
    -0.08
     både
    -0.07
     Both
    -0.07
     accordingly
    -0.07
    evenodd
    -0.07
     ambos
    -0.06
    oreach
    -0.06
     both
    -0.06
     BOTH
    -0.06
    decltype
    -0.06
    POSITIVE LOGITS
     nor
    0.15
     other
    0.13
     anymore
    0.13
     any
    0.11
    nor
    0.10
    other
    0.10
     Nor
    0.09
     necessarily
    0.09
     or
    0.09
    Nor
    0.09
    Activations Density 0.026%

    No Known Activations