© 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. 61055
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements and their societal impact

    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
    éijij
    -0.07
    anni
    -0.07
    ichen
    -0.07
    åĿª
    -0.07
    [".
    -0.07
    ancel
    -0.07
    onica
    -0.07
    zem
    -0.07
    dra
    -0.07
     लà¤ķ
    -0.07
    POSITIVE LOGITS
     local
    0.08
     Local
    0.07
     project
    0.07
     during
    0.07
     During
    0.07
     locally
    0.07
     construction
    0.06
     Project
    0.06
    0.06
    local
    0.06
    Activations Density 0.010%

    No Known Activations