© 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. 89711
    Prev
    Next
    INDEX
    Explanations

    intense emotional adjectives and descriptors related to character and narrative depth

    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
    auga
    -0.08
    asca
    -0.07
    .gdx
    -0.07
    uchsia
    -0.06
    _HERSHEY
    -0.06
    oen
    -0.06
     Cah
    -0.06
    мена
    -0.06
     newIndex
    -0.06
    ylie
    -0.06
    POSITIVE LOGITS
    adlo
    0.07
     mimo
    0.07
     essen
    0.07
     mev
    0.06
    ÏĥÏĦα
    0.06
    åĿĬ
    0.06
    oya
    0.06
     деÑı
    0.06
     lesbi
    0.06
     bdsm
    0.06
    Activations Density 0.115%

    No Known Activations