© 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. 116350
    Prev
    Next
    INDEX
    Explanations

    information related to television programming and schedules

    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
     nhau
    -0.07
    ItemCount
    -0.06
    ilm
    -0.06
     Jones
    -0.06
    apro
    -0.06
    DMI
    -0.06
    elles
    -0.06
    exels
    -0.06
    hausen
    -0.06
    rone
    -0.06
    POSITIVE LOGITS
    verb
    0.06
    Ñĩик
    0.06
    ẩm
    0.06
    ooth
    0.06
    idden
    0.06
     NBC
    0.06
    inker
    0.06
     Conserv
    0.06
    bon
    0.06
    witter
    0.06
    Activations Density 0.033%

    No Known Activations