© 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. 121064
    Prev
    Next
    INDEX
    Explanations

    expressions related to starting players in sports contexts

    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
    ализи
    -0.09
    asse
    -0.08
    istica
    -0.07
    oust
    -0.07
     nackte
    -0.07
    verity
    -0.07
    TEMPL
    -0.07
    éal
    -0.07
    greg
    -0.07
    `.`
    -0.07
    POSITIVE LOGITS
    olut
    0.06
    rtype
    0.06
    ally
    0.06
    ial
    0.06
    nable
    0.06
    eru
    0.06
     throughout
    0.05
     dem
    0.05
     worship
    0.05
     wars
    0.05
    Activations Density 0.005%

    No Known Activations