© 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. 98784
    Prev
    Next
    INDEX
    Explanations

    phrases related to scoring and predictions in sports events

    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
    ointments
    -0.07
    ابر
    -0.07
    antha
    -0.07
    rok
    -0.06
     Bris
    -0.06
     AQ
    -0.06
    _OPTS
    -0.06
     pä
    -0.06
    ีà¸Ķ
    -0.06
     queryInterface
    -0.06
    POSITIVE LOGITS
    isse
    0.07
    immel
    0.06
    andum
    0.06
    icut
    0.06
    /welcome
    0.06
    avel
    0.06
    isce
    0.05
    ista
    0.05
    edom
    0.05
     Bat
    0.05
    Activations Density 0.000%

    No Known Activations