© 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. 63089
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence and popularity of specific items or topics

    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
     POW
    -0.06
    SD
    -0.06
    598
    -0.06
    904
    -0.06
    631
    -0.06
    à¹Ĥ
    -0.06
    ollower
    -0.06
    open
    -0.06
    iven
    -0.06
    Tables
    -0.05
    POSITIVE LOGITS
    inue
    0.08
    룬
    0.07
     Glas
    0.07
    eded
    0.07
    µ
    0.07
    à§į
    0.06
    atism
    0.06
    оÑĢдин
    0.06
    ickle
    0.06
    yre
    0.06
    Activations Density 0.004%

    No Known Activations