© 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. 14105
    Prev
    Next
    INDEX
    Explanations

    references to security systems and operations

    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
    iegel
    -0.08
    ulers
    -0.06
    æ¥Ń
    -0.06
    ãģķãģ¾
    -0.06
    olumn
    -0.06
    elt
    -0.06
    ested
    -0.06
     blueprint
    -0.06
     toc
    -0.06
    PLE
    -0.06
    POSITIVE LOGITS
     intelligence
    0.10
     Intelligence
    0.09
    intelligence
    0.08
     analysts
    0.07
     intel
    0.07
    สà¸ģ
    0.07
    æĥħåł±
    0.07
    //{{
    0.07
     Analyst
    0.06
     pri
    0.06
    Activations Density 0.003%

    No Known Activations