© 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. 97789
    Prev
    Next
    INDEX
    Explanations

    terms related to positions in sports, particularly baseball

    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
    ><![
    -0.08
    etas
    -0.08
    isle
    -0.07
    ETA
    -0.07
    coni
    -0.07
    eta
    -0.07
    feito
    -0.07
    allis
    -0.07
    feed
    -0.07
    qrt
    -0.07
    POSITIVE LOGITS
    sm
    0.07
    earer
    0.06
    ®
    0.06
    VERRIDE
    0.06
     diffuse
    0.06
     Wagner
    0.06
    ·
    0.05
    §
    0.05
    ers
    0.05
    Coder
    0.05
    Activations Density 0.003%

    No Known Activations