© 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. 18509
    Prev
    Next
    INDEX
    Explanations

    descriptions of contrasting settings and socioeconomic conditions

    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
    jang
    -0.07
    ustos
    -0.07
    oho
    -0.07
     occas
    -0.07
    ovel
    -0.07
    ocha
    -0.07
     Ukr
    -0.07
    ÏĥÏĢ
    -0.06
    otre
    -0.06
    esome
    -0.06
    POSITIVE LOGITS
     Dubai
    0.09
     oil
    0.08
     Arabian
    0.08
     Gulf
    0.07
     desert
    0.07
     Desert
    0.07
     Oil
    0.07
     pet
    0.07
     city
    0.06
    riba
    0.06
    Activations Density 0.007%

    No Known Activations