© 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. 2734
    Prev
    Next
    INDEX
    Explanations

    instructions or actions related to interacting with software or games

    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
    ening
    -0.07
    anner
    -0.07
     nud
    -0.06
     Decode
    -0.06
    anners
    -0.06
     Chill
    -0.06
     indem
    -0.06
    rab
    -0.06
     Smooth
    -0.06
    oust
    -0.06
    POSITIVE LOGITS
    ÎŃαÏĤ
    0.07
    tle
    0.07
    lopedia
    0.07
    ÑĢеÑģ
    0.07
    olar
    0.06
    _attachments
    0.06
    ewood
    0.06
    aturated
    0.06
    uju
    0.06
    AMAGE
    0.06
    Activations Density 0.010%

    No Known Activations