© 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. 121449
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and its various applications

    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
    ãģĵãĤį
    -0.09
    rang
    -0.07
    rong
    -0.07
    abl
    -0.06
    gings
    -0.06
     PROF
    -0.06
    erable
    -0.06
     architekt
    -0.06
     Elias
    -0.06
    ainless
    -0.06
    POSITIVE LOGITS
    istically
    0.07
    -created
    0.07
    éĿ©
    0.07
    ificial
    0.07
    çļĦãģ«
    0.07
     Intelligence
    0.07
    ropoda
    0.06
     intelligence
    0.06
    swana
    0.06
     Monthly
    0.06
    Activations Density 0.014%

    No Known Activations