© 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. 38521
    Prev
    Next
    INDEX
    Explanations

    names of notable political figures and references to political 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
     ìļ
    -0.09
    .Apis
    -0.08
    itty
    -0.08
    سط
    -0.08
     Kaynak
    -0.07
    iddy
    -0.07
    ãĢ
    -0.07
     barg
    -0.07
    à¹ĥà¸Ī
    -0.07
    ëĿ½
    -0.07
    POSITIVE LOGITS
    idle
    0.06
    Parser
    0.06
     retina
    0.06
    IntArray
    0.06
    µ¬
    0.06
    RTC
    0.05
    tti
    0.05
    endor
    0.05
    issance
    0.05
    stoupil
    0.05
    Activations Density 0.005%

    No Known Activations