© 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 EvalsExportsAPI 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. 82882
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to automotive components

    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
     fraud
    -0.06
    paper
    -0.06
    IPA
    -0.06
     Powerful
    -0.06
    yro
    -0.06
    ongo
    -0.06
    sey
    -0.06
    hir
    -0.05
    åĵ¡
    -0.05
     powerful
    -0.05
    POSITIVE LOGITS
     Jeg
    0.08
     Installation
    0.08
     OE
    0.08
    Installation
    0.07
     installation
    0.07
    ordered
    0.07
     unordered
    0.07
     bil
    0.07
     ordering
    0.07
     Ordering
    0.07
    Activations Density 0.012%

    No Known Activations