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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82326
    Prev
    Next
    INDEX
    Explanations

    mentions of specific brands or products

    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
    orang
    -0.08
    rung
    -0.08
    orf
    -0.07
     araya
    -0.07
    inent
    -0.06
    wart
    -0.06
    ت
    -0.06
    iment
    -0.06
    unge
    -0.06
    lotte
    -0.06
    POSITIVE LOGITS
     fa
    0.07
     Fa
    0.07
    ground
    0.07
    ima
    0.07
     FA
    0.07
    .fa
    0.06
    olan
    0.06
    aliyet
    0.06
    /fa
    0.06
    ust
    0.06
    Activations Density 0.008%

    No Known Activations