© 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. 128821
    Prev
    Next
    INDEX
    Explanations

    instances of the word "led" in various 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
    /U
    -0.07
    >\<
    -0.07
    arians
    -0.07
    asons
    -0.07
    eting
    -0.07
    ishly
    -0.06
    ppo
    -0.06
    imeo
    -0.06
    iesz
    -0.06
    ilor
    -0.06
    POSITIVE LOGITS
    gers
    0.09
    argo
    0.07
     us
    0.07
    -edge
    0.07
     astr
    0.07
    ziej
    0.06
     to
    0.06
    625
    0.06
    hlen
    0.06
    orris
    0.06
    Activations Density 0.015%

    No Known Activations