© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15294
    Prev
    Next
    INDEX
    Explanations

    references to automation and control systems in engineering and technology contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Priv
    -0.06
     Screening
    -0.06
    707
    -0.06
     Prepared
    -0.06
     procedure
    -0.06
     anchor
    -0.06
     tre
    -0.05
     Hutch
    -0.05
     kind
    -0.05
    uja
    -0.05
    POSITIVE LOGITS
    æݧåĪ¶
    0.12
     control
    0.11
     controlling
    0.11
    control
    0.11
     controllers
    0.11
    -control
    0.10
     controller
    0.10
     controls
    0.10
     kontrol
    0.10
     Control
    0.10
    Activations Density 0.067%

    No Known Activations