© 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 EvalsExportsinterp-engineNEWAPI 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. 97662
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements and expressions of enthusiasm or emphasis

    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
    liÄį
    -0.07
    ongyang
    -0.07
    mani
    -0.07
    Ìĥ
    -0.07
    ÙİØ©
    -0.07
    oby
    -0.07
     migrationBuilder
    -0.06
    onio
    -0.06
    ापà¤ķ
    -0.06
    ÙĴب
    -0.06
    POSITIVE LOGITS
    zos
    0.09
    vas
    0.06
    ãĥ¼ãĥij
    0.06
    usu
    0.06
    Delayed
    0.06
    allee
    0.06
    REV
    0.06
    ertz
    0.06
     Ducks
    0.06
     Biblical
    0.06
    Activations Density 0.034%

    No Known Activations