© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15636
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals and their roles in various contexts, especially connected to entertainment and celebrity culture

    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
    ekt
    -0.07
    gnu
    -0.07
    ixed
    -0.06
    okud
    -0.06
    udge
    -0.06
    createClass
    -0.06
    loh
    -0.06
    isque
    -0.06
    atisch
    -0.06
    FG
    -0.06
    POSITIVE LOGITS
    arin
    0.07
    LineEdit
    0.07
    \grid
    0.07
    UBE
    0.07
    ãĥªãĤ«
    0.06
    TriState
    0.06
    mir
    0.06
    encer
    0.06
     åĩ
    0.06
    /thread
    0.06
    Activations Density 0.020%

    No Known Activations