© 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. 38522
    Prev
    Next
    INDEX
    Explanations

    references to television show airing schedules and events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ras
    -0.07
    adows
    -0.06
    ahun
    -0.06
     Dawn
    -0.06
    ilda
    -0.06
    rawn
    -0.06
     camps
    -0.06
    zeichnet
    -0.06
    iec
    -0.06
     year
    -0.06
    POSITIVE LOGITS
     episode
    0.07
    episode
    0.07
    esson
    0.06
    zig
    0.06
     tonight
    0.06
    骨
    0.06
    PTH
    0.06
    à¸Ĭม
    0.06
    sob
    0.06
    thr
    0.06
    Activations Density 0.028%

    No Known Activations