© 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. 83783
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers (DOIs) and related references in scientific literature

    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
    idd
    -0.08
    esda
    -0.07
    ifu
    -0.07
    chio
    -0.06
    atern
    -0.06
    ÑĮко
    -0.06
    iah
    -0.06
    ãĤ¹ãĤ¯
    -0.06
    thon
    -0.06
    oust
    -0.06
    POSITIVE LOGITS
     Bender
    0.07
     Zuk
    0.06
    astro
    0.06
    geo
    0.06
    že
    0.06
     EntityState
    0.06
    imetype
    0.06
     Dün
    0.06
    odus
    0.06
    icode
    0.06
    Activations Density 0.003%

    No Known Activations