© 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. 53893
    Prev
    Next
    INDEX
    Explanations

    references to essential amenities and quality of life features

    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
     treff
    -0.08
    mscorlib
    -0.07
    ازÛĮ
    -0.07
    rious
    -0.07
    herits
    -0.07
    ationship
    -0.07
    iqueta
    -0.07
    uled
    -0.07
    åĹ
    -0.07
    rij
    -0.07
    POSITIVE LOGITS
     rage
    0.07
     trim
    0.07
     attention
    0.06
     mak
    0.06
     Abstract
    0.06
    Abstract
    0.06
    æĸ¹
    0.06
    GER
    0.06
     ger
    0.05
    _ASC
    0.05
    Activations Density 0.013%

    No Known Activations