© 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. 70601
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms related to companies and financial institutions

    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
    ooter
    -0.08
    itoris
    -0.07
    overs
    -0.07
    eness
    -0.07
    inkel
    -0.07
    @Web
    -0.07
    ields
    -0.07
     Overs
    -0.07
    rá
    -0.06
    idunt
    -0.06
    POSITIVE LOGITS
    acha
    0.07
    #ac
    0.07
    Uvs
    0.07
    lexport
    0.06
    AtA
    0.06
    ullivan
    0.06
    SupportedContent
    0.06
    ople
    0.06
    otti
    0.06
    stag
    0.06
    Activations Density 0.011%

    No Known Activations