© 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. 15905
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and responses

    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
    eting
    -0.06
    pers
    -0.06
    is
    -0.06
    ands
    -0.06
     Hass
    -0.06
     line
    -0.05
    and
    -0.05
     al
    -0.05
     tens
    -0.05
    ading
    -0.05
    POSITIVE LOGITS
    eyJ
    0.07
    é
    0.07
    xon
    0.07
    FER
    0.07
    astle
    0.07
    oje
    0.07
    xbc
    0.07
    alc
    0.07
    engo
    0.07
    |{↵
    0.07
    Activations Density 0.010%

    No Known Activations