© 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. 79096
    Prev
    Next
    INDEX
    Explanations

    phrases related to capturing or seizing actions

    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
    ISIBLE
    -0.07
     fitte
    -0.06
    ÏĪε
    -0.06
    ambient
    -0.06
    .gameserver
    -0.06
     Cli
    -0.06
    aukee
    -0.06
    miner
    -0.05
     misd
    -0.05
     mism
    -0.05
    POSITIVE LOGITS
     custody
    0.07
    rian
    0.06
    elps
    0.06
    ziej
    0.06
     cust
    0.06
     hostage
    0.06
    agos
    0.06
    ennie
    0.06
    hunt
    0.06
    arty
    0.06
    Activations Density 0.038%

    No Known Activations