© 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. 53944
    Prev
    Next
    INDEX
    Explanations

    keywords related to business operations and customer interactions

    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
     Mit
    -0.06
    Mit
    -0.06
    essen
    -0.06
    opa
    -0.06
    itted
    -0.06
    iswa
    -0.06
     mit
    -0.05
    elden
    -0.05
    iske
    -0.05
    eln
    -0.05
    POSITIVE LOGITS
     Nug
    0.07
     reputation
    0.07
    bread
    0.07
     pena
    0.07
    written
    0.07
     Reputation
    0.07
    :async
    0.06
     è©ķ
    0.06
    ób
    0.06
    compat
    0.06
    Activations Density 0.016%

    No Known Activations