© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 126565
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "champion" in various contexts

    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
    -China
    -0.07
    ulus
    -0.07
    ty
    -0.07
    ülü
    -0.07
    anded
    -0.07
    SED
    -0.07
    -0.07
    ãĤ¤ãĤ¯
    -0.07
    utron
    -0.06
    DSA
    -0.06
    POSITIVE LOGITS
    nat
    0.08
    SHIP
    0.08
    /current
    0.07
    cy
    0.07
    ships
    0.07
    ../../../
    0.07
    avier
    0.07
    eshire
    0.07
     Anything
    0.07
    edReader
    0.06
    Activations Density 0.007%

    No Known Activations