© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71055
    Prev
    Next
    INDEX
    Explanations

    terms related to prestigious football tournaments and leagues

    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
    大åħ¨
    -0.08
    tual
    -0.06
     Zi
    -0.06
    ãĤĩ
    -0.06
    ãĤĽ
    -0.06
    üns
    -0.06
    OKIE
    -0.06
     boh
    -0.06
     Hak
    -0.06
    UNIT
    -0.05
    POSITIVE LOGITS
    iap
    0.07
    lite
    0.07
    caf
    0.07
    rans
    0.07
    ":[{↵
    0.06
    icut
    0.06
    nat
    0.06
    ornecedor
    0.06
    lat
    0.06
    /../
    0.06
    Activations Density 0.001%

    No Known Activations