© 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. 17-LLAMASCOPE-RES-131K
    6. 71475
    Prev
    Next
    INDEX
    Explanations

    descriptions of luxurious experiences or offerings

    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
    etat
    -0.08
    alendar
    -0.07
    817
    -0.06
     Leonard
    -0.06
     tsl
    -0.06
    ÃŃcio
    -0.06
    Eu
    -0.06
    eÄį
    -0.06
    vironment
    -0.06
    Purpose
    -0.06
    POSITIVE LOGITS
     åº
    0.07
    ten
    0.06
    íĴĪ
    0.06
     Giov
    0.06
     Huff
    0.06
    usz
    0.06
    ilyn
    0.06
    lassen
    0.06
     unlocks
    0.05
     anniversary
    0.05
    Activations Density 0.008%

    No Known Activations