© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88303
    Prev
    Next
    INDEX
    Explanations

    technical terms and labels related to programming or data processing

    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
    allet
    -0.07
    اÙ쨱
    -0.06
    ActionCreators
    -0.06
    ÑĢедел
    -0.06
    idebar
    -0.06
    MBER
    -0.06
     middleware
    -0.06
    NAS
    -0.06
    AREST
    -0.06
    Ws
    -0.06
    POSITIVE LOGITS
    onda
    0.06
    ÅĻÃŃž
    0.06
    rtc
    0.06
    ntp
    0.06
    anker
    0.06
     McGr
    0.06
     content
    0.06
    inke
    0.06
     Baz
    0.06
    vik
    0.06
    Activations Density 0.001%

    No Known Activations