© 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. 15-LLAMASCOPE-RES-131K
    11. 62031
    Prev
    Next
    INDEX
    Explanations

    references to different forms and types of medications or supplements

    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
    IGH
    -0.07
    /customer
    -0.07
     Slater
    -0.06
     Kimber
    -0.06
    t
    -0.06
    ked
    -0.06
     Obr
    -0.06
    /layouts
    -0.06
    /security
    -0.06
    ese
    -0.06
    POSITIVE LOGITS
    stÅĻed
    0.08
    ÑĦек
    0.08
    imson
    0.07
    ãģ»ãģĨ
    0.07
    odelist
    0.07
    Å¡el
    0.07
    -based
    0.07
    /array
    0.07
    -format
    0.07
    utex
    0.07
    Activations Density 0.022%

    No Known Activations