© 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. 123400
    Prev
    Next
    INDEX
    Explanations

    content related to television broadcasts and their 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
     spotted
    -0.06
    eroon
    -0.06
    427
    -0.06
     system
    -0.05
     spot
    -0.05
     buff
    -0.05
     Wake
    -0.05
    osemite
    -0.05
    008
    -0.05
     partic
    -0.05
    POSITIVE LOGITS
     coverage
    0.09
    coverage
    0.09
     Coverage
    0.08
    macros
    0.07
     sublic
    0.07
    Handled
    0.07
    -rights
    0.07
    Coverage
    0.07
    #ac
    0.07
    ãģĭãģĦ
    0.07
    Activations Density 0.023%

    No Known Activations