© 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. 17-LLAMASCOPE-RES-131K
    11. 15553
    Prev
    Next
    INDEX
    Explanations

    references to selection processes and applications related to sporting teams

    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
    öy
    -0.07
     UFC
    -0.07
     ziy
    -0.07
     serialVersionUID
    -0.06
    xC
    -0.06
    IVER
    -0.06
     Bachelor
    -0.06
    arro
    -0.06
    åĶ
    -0.06
     Fior
    -0.06
    POSITIVE LOGITS
     season
    0.07
    Sprites
    0.06
    enance
    0.06
    abilit
    0.06
    mage
    0.06
    yme
    0.06
     parent
    0.06
    家åºŃ
    0.06
    umann
    0.06
    578
    0.06
    Activations Density 0.015%

    No Known Activations