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

    Neuronpedia

    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. 60582
    Prev
    Next
    INDEX
    Explanations

    discussions related to automotive design and performance

    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
    /import
    -0.07
    439
    -0.07
    elize
    -0.07
    amba
    -0.07
    dep
    -0.06
    ยม
    -0.06
     Helm
    -0.06
     Mechanics
    -0.06
    339
    -0.06
     Exercise
    -0.06
    POSITIVE LOGITS
    -purpose
    0.10
     versatile
    0.10
     purpose
    0.09
     versatility
    0.08
     vers
    0.08
    нÑĸвеÑĢ
    0.08
     general
    0.08
     *(*
    0.08
    purpose
    0.08
    urpose
    0.08
    Activations Density 0.048%

    No Known Activations