© 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. 117010
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical wiring and installation tasks

    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
    ENN
    -0.06
    Ì
    -0.06
     trend
    -0.06
    otton
    -0.06
     pipeline
    -0.06
    anou
    -0.06
    born
    -0.06
     dust
    -0.05
    .shtml
    -0.05
    /dev
    -0.05
    POSITIVE LOGITS
    ëł
    0.08
    NamedQuery
    0.07
    isko
    0.07
    StackNavigator
    0.07
    ogi
    0.07
    oui
    0.07
    /ml
    0.07
    æľĭ
    0.07
    arden
    0.07
    ád
    0.07
    Activations Density 0.002%

    No Known Activations