© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4278
    Prev
    Next
    INDEX
    Explanations

    references to sports and player statistics

    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
     -*-č↵
    -0.09
    eÄį
    -0.08
    RunLoop
    -0.08
     Bale
    -0.08
     å¾ĴæŃ©
    -0.08
    ãĤıãĤĮ
    -0.07
    ectl
    -0.07
    _TOO
    -0.07
    inness
    -0.07
    ,eg
    -0.07
    POSITIVE LOGITS
    hire
    0.06
     With
    0.06
     with
    0.06
     Sports
    0.06
     Mission
    0.06
     after
    0.06
     while
    0.06
     re
    0.06
     No
    0.05
     Matt
    0.05
    Activations Density 0.028%

    No Known Activations