© 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. 76685
    Prev
    Next
    INDEX
    Explanations

    references to labor-related compensation and pay structures

    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
    elize
    -0.07
    ruary
    -0.07
     Ñħод
    -0.07
    pell
    -0.07
    smarty
    -0.07
    entes
    -0.07
    ibase
    -0.07
    xba
    -0.06
    gfx
    -0.06
    ittest
    -0.06
    POSITIVE LOGITS
    ormal
    0.06
     overtime
    0.06
    anter
    0.06
     Fulton
    0.06
    .Retrofit
    0.06
    armor
    0.06
    GC
    0.06
    å°ıæŶ
    0.06
    æ½®
    0.06
     hours
    0.05
    Activations Density 0.003%

    No Known Activations