© 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. 86070
    Prev
    Next
    INDEX
    Explanations

    punctuations and quotes in the text

    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
    edy
    -0.07
    len
    -0.07
    zk
    -0.07
    dub
    -0.07
    ose
    -0.06
    ewe
    -0.06
     kvinne
    -0.06
    HQ
    -0.06
     zwar
    -0.06
    okens
    -0.06
    POSITIVE LOGITS
    s
    0.12
    sing
    0.08
    Ùĩ
    0.08
    ÂĿ
    0.08
    es
    0.08
    sak
    0.07
    न
    0.07
    enler
    0.07
     âĢı
    0.07
    sian
    0.07
    Activations Density 0.033%

    No Known Activations