© 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. 78110
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and institutions

    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
    ulas
    -0.07
    ·»
    -0.07
    LLLL
    -0.06
    isNull
    -0.06
    _msgs
    -0.06
    led
    -0.06
     trag
    -0.06
    ullet
    -0.06
    ldata
    -0.06
    966
    -0.06
    POSITIVE LOGITS
    isu
    0.07
    usu
    0.06
     Freeman
    0.06
    ISCO
    0.06
     Obr
    0.06
     гÑĸд
    0.06
    arih
    0.06
     defaultProps
    0.06
     Jones
    0.06
     CST
    0.06
    Activations Density 0.001%

    No Known Activations