© 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. 63174
    Prev
    Next
    INDEX
    Explanations

    references to social media and digital content platforms

    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
     ÑĪÑĤ
    -0.06
    ester
    -0.06
    _FB
    -0.06
     flam
    -0.06
    Enlarge
    -0.06
    زد
    -0.06
    YLES
    -0.06
    ynchronous
    -0.06
    esti
    -0.06
    ÙIJÙħ
    -0.06
    POSITIVE LOGITS
    otive
    0.07
     Wayback
    0.06
    ķìĿ¸
    0.06
    éĻ¢
    0.06
    createView
    0.06
    baugh
    0.06
     RectTransform
    0.06
    lap
    0.06
    quisites
    0.06
     Wrapped
    0.06
    Activations Density 0.003%

    No Known Activations