© 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. 123525
    Prev
    Next
    INDEX
    Explanations

    details about characters' professions and backgrounds

    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
    aeper
    -0.09
    RecognitionException
    -0.09
    aticon
    -0.08
    illez
    -0.08
    ноз
    -0.08
    iesta
    -0.07
    raç
    -0.07
    agra
    -0.07
    à¸ı
    -0.07
    ecn
    -0.07
    POSITIVE LOGITS
    377
    0.06
     stat
    0.06
     Meadows
    0.06
     reluctantly
    0.06
     Morales
    0.05
    /logger
    0.05
    женÑĮ
    0.05
     PD
    0.05
     Collins
    0.05
     ambit
    0.05
    Activations Density 0.025%

    No Known Activations