© 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. 104013
    Prev
    Next
    INDEX
    Explanations

    phrases related to inquiries and obtaining information

    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
    ê·¼
    -0.07
     treff
    -0.06
    iri
    -0.06
    ornings
    -0.06
    ازÙĩ
    -0.06
    ves
    -0.06
    Ùĩار
    -0.06
    900
    -0.06
    allen
    -0.06
     YÃĸ
    -0.06
    POSITIVE LOGITS
    ï¼Į请
    0.08
     yourself
    0.08
    Ñħодим
    0.07
    egin
    0.07
    storybook
    0.07
    dale
    0.07
    raquo
    0.07
     trá»Ŀi
    0.07
    ilder
    0.07
    dre
    0.07
    Activations Density 0.017%

    No Known Activations