© 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. 80684
    Prev
    Next
    INDEX
    Explanations

    phrases that express personal insights or experiences

    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
    owie
    -0.08
    avra
    -0.07
    opian
    -0.07
     Martins
    -0.07
    ÑĮ
    -0.06
    499
    -0.06
    rame
    -0.06
    ilver
    -0.06
     Morrow
    -0.06
    onis
    -0.06
    POSITIVE LOGITS
     therefore
    0.08
     donc
    0.07
    -tm
    0.07
     Therefore
    0.06
     nên
    0.06
    ITCH
    0.06
    achs
    0.06
     supposed
    0.06
    vant
    0.06
     expected
    0.06
    Activations Density 0.029%

    No Known Activations