© 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. 56147
    Prev
    Next
    INDEX
    Explanations

    phrases associated with sports rules and controversial actions during games

    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
    quential
    -0.07
    jÃŃ
    -0.06
    asca
    -0.06
    loquent
    -0.06
     hang
    -0.06
    acz
    -0.06
    Latch
    -0.06
     depth
    -0.06
     Current
    -0.06
     baÅŁÄ±na
    -0.06
    POSITIVE LOGITS
     offic
    0.09
    refs
    0.08
     rulings
    0.08
    UBE
    0.07
     Officials
    0.07
    ersed
    0.07
    richt
    0.07
    Officials
    0.07
    gii
    0.07
    ref
    0.07
    Activations Density 0.023%

    No Known Activations