© 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. 9-LLAMASCOPE-RES-131K
    11. 96282
    Prev
    Next
    INDEX
    Explanations

    references to scientific research and expeditions

    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
    entes
    -0.07
     contra
    -0.07
     Selling
    -0.07
    htt
    -0.06
     selling
    -0.06
    emez
    -0.06
    andr
    -0.06
     context
    -0.06
    -sizing
    -0.06
    ullan
    -0.06
    POSITIVE LOGITS
    enu
    0.06
     Visibility
    0.06
    resolved
    0.06
     Burnett
    0.06
    _ep
    0.06
     dispersed
    0.06
    ='".$_
    0.06
     Resolve
    0.06
    ioned
    0.06
    .neo
    0.06
    Activations Density 0.011%

    No Known Activations