© 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. 15-LLAMASCOPE-RES-131K
    11. 86305
    Prev
    Next
    INDEX
    Explanations

    terms related to historical or administrative entities

    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
    PACE
    -0.07
    eyen
    -0.07
    fragistics
    -0.07
    iyim
    -0.07
    pek
    -0.07
    oin
    -0.07
    åīĽ
    -0.07
    Ïģά
    -0.07
    .mybatisplus
    -0.07
    ophobia
    -0.07
    POSITIVE LOGITS
    /admin
    0.07
    /legal
    0.07
     instruments
    0.06
    urga
    0.06
    185
    0.06
     Bay
    0.05
     Heater
    0.05
     Cathy
    0.05
    omers
    0.05
    ayar
    0.05
    Activations Density 0.005%

    No Known Activations