© 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. 5981
    Prev
    Next
    INDEX
    Explanations

    references to dates and timelines in a political context

    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
    $__
    -0.07
    jeme
    -0.07
    hausen
    -0.07
    osate
    -0.07
    fest
    -0.07
    596
    -0.06
    ĥn
    -0.06
    ÑĢави
    -0.06
    صاÙĦ
    -0.06
    slaught
    -0.06
    POSITIVE LOGITS
     appointment
    0.08
     Appointment
    0.07
     office
    0.07
     resignation
    0.07
     Track
    0.07
    avir
    0.06
    ç¬
    0.06
    ارج
    0.06
     appointments
    0.06
    ista
    0.06
    Activations Density 0.021%

    No Known Activations