© 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. 26972
    Prev
    Next
    INDEX
    Explanations

    expressions of affection and enjoyment related to various activities and places

    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
    odo
    -0.08
    \Abstract
    -0.06
    quer
    -0.06
     Wit
    -0.06
    247
    -0.05
    162
    -0.05
    inating
    -0.05
    iliar
    -0.05
    param
    -0.05
    ories
    -0.05
    POSITIVE LOGITS
    _Generic
    0.08
    ë¹ĦìĬ¤
    0.07
    acob
    0.07
    .Glide
    0.07
    ByKey
    0.07
    åĴ²
    0.07
    ToOne
    0.07
    GetPosition
    0.07
    ê¸ī
    0.07
     parte
    0.07
    Activations Density 0.025%

    No Known Activations