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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57524
    Prev
    Next
    INDEX
    Explanations

    elements related to teamwork and interaction in challenging situations

    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
    wart
    -0.07
    192
    -0.07
    193
    -0.06
    riot
    -0.06
     worldwide
    -0.06
     Vita
    -0.06
    enberg
    -0.06
     remot
    -0.06
    igit
    -0.05
    irit
    -0.05
    POSITIVE LOGITS
    ocha
    0.07
    .hd
    0.07
    izr
    0.06
     McMaster
    0.06
    ints
    0.06
    -Control
    0.06
    itom
    0.06
     ê°ĻìĬµëĭĪëĭ¤
    0.06
     intf
    0.06
    οÏħμε
    0.06
    Activations Density 0.002%

    No Known Activations