© 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. 9-LLAMASCOPE-RES-131K
    11. 96369
    Prev
    Next
    INDEX
    Explanations

    references to actions and interactions involving individuals

    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
    sson
    -0.07
     ngh
    -0.07
     volumes
    -0.07
    åĭĴ
    -0.07
    ione
    -0.06
    ppers
    -0.06
     Sabb
    -0.06
    оÑĢд
    -0.06
    ål
    -0.06
    xo
    -0.06
    POSITIVE LOGITS
    §
    0.06
     weather
    0.06
     er
    0.06
    modo
    0.06
    getChild
    0.06
    ¹
    0.06
    afi
    0.06
     Tanner
    0.06
     Weather
    0.05
    QR
    0.05
    Activations Density 0.069%

    No Known Activations