© 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. 9-LLAMASCOPE-RES-131K
    11. 96523
    Prev
    Next
    INDEX
    Explanations

    elements related to sports events and player actions

    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
    ILT
    -0.07
    forme
    -0.06
    stre
    -0.06
     Dudley
    -0.06
    woo
    -0.06
    emann
    -0.05
    224
    -0.05
     pl
    -0.05
     Lud
    -0.05
     Clamp
    -0.05
    POSITIVE LOGITS
    lobal
    0.08
    IRO
    0.07
    jh
    0.07
    ÑĨенÑĤÑĢа
    0.07
    ifax
    0.07
    inae
    0.07
     tam
    0.07
    alse
    0.07
     defaultCenter
    0.06
     adet
    0.06
    Activations Density 0.040%

    No Known Activations