© 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. 118039
    Prev
    Next
    INDEX
    Explanations

    references to controlling digital inputs and outputs in a programming context

    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
    çij
    -0.07
    ESP
    -0.07
    chn
    -0.06
    ichten
    -0.06
     tun
    -0.06
    ake
    -0.06
    .flush
    -0.06
     tú
    -0.06
     tuner
    -0.06
    979
    -0.06
    POSITIVE LOGITS
    /libs
    0.07
     currentState
    0.06
     Animalia
    0.06
     Fee
    0.06
    undry
    0.06
    okol
    0.06
    Raster
    0.06
    YN
    0.06
    razier
    0.06
    riet
    0.06
    Activations Density 0.022%

    No Known Activations