© 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. 95980
    Prev
    Next
    INDEX
    Explanations

    text related to scientific topics or subjects

    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
    ãģĿ
    -0.07
    маз
    -0.07
    ij¸
    -0.06
    _Mode
    -0.06
    ắt
    -0.06
    imli
    -0.06
     æĹ
    -0.06
    fn
    -0.06
    uÅŁ
    -0.06
     quarters
    -0.06
    POSITIVE LOGITS
    uja
    0.06
     Guerrero
    0.06
    UY
    0.06
    hir
    0.06
    nia
    0.06
    aint
    0.06
     ire
    0.06
    na
    0.06
    loyd
    0.06
    nal
    0.06
    Activations Density 0.006%

    No Known Activations