© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    variables related to environmental conditions and their effects

    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
    omik
    -0.08
    rana
    -0.07
    Ä°T
    -0.06
    bsd
    -0.06
    ostel
    -0.06
    çĽijåIJ¬é¡µéĿ¢
    -0.06
     Grund
    -0.06
    386
    -0.06
     UIL
    -0.06
    baz
    -0.06
    POSITIVE LOGITS
     unlike
    0.08
     environments
    0.07
     Ging
    0.07
     thanks
    0.07
    adero
    0.07
     Thanks
    0.07
     situations
    0.07
    à¹Ħà¸Ķ
    0.07
     climates
    0.06
    ingham
    0.06
    Activations Density 0.031%

    No Known Activations