© 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. 9-LLAMASCOPE-RES-131K
    11. 99146
    Prev
    Next
    INDEX
    Explanations

    terms related to political oppression and regimes

    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
    meer
    -0.07
    andest
    -0.07
     chem
    -0.07
    _READY
    -0.06
     billig
    -0.06
    olla
    -0.06
    hangi
    -0.06
    ;++
    -0.06
    idor
    -0.06
    bere
    -0.06
    POSITIVE LOGITS
    okens
    0.06
     alien
    0.06
    ipple
    0.06
    ForKey
    0.06
     Alien
    0.06
     Cruise
    0.06
    odon
    0.06
    uchs
    0.06
    okies
    0.06
    ANC
    0.06
    Activations Density 0.062%

    No Known Activations