© 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. 106540
    Prev
    Next
    INDEX
    Explanations

    numerical data and financial terminology related to sports clubs

    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
    èħ
    -0.07
    creens
    -0.07
    ingles
    -0.07
    ampo
    -0.07
    uration
    -0.06
    Locator
    -0.06
    gis
    -0.06
    entre
    -0.06
     Phaser
    -0.06
    .pm
    -0.06
    POSITIVE LOGITS
    ãĥĥãĥĹ
    0.07
    obo
    0.07
     spending
    0.07
     revenue
    0.07
     financial
    0.07
     imper
    0.07
     Revenue
    0.07
     club
    0.06
     Gest
    0.06
     Financial
    0.06
    Activations Density 0.003%

    No Known Activations