© 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. 129717
    Prev
    Next
    INDEX
    Explanations

    references to various types of items or materials

    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
    bsolute
    -0.07
    andest
    -0.07
    celed
    -0.07
    essen
    -0.07
    lea
    -0.07
    ence
    -0.06
     Dumpster
    -0.06
    ymous
    -0.06
    ial
    -0.06
    bourne
    -0.06
    POSITIVE LOGITS
    /services
    0.08
     happening
    0.08
    ToDo
    0.08
    linger
    0.07
    迹
    0.07
    æł·çļĦ
    0.07
     Happ
    0.07
    iness
    0.07
    ÛĮز
    0.07
    sburg
    0.07
    Activations Density 0.009%

    No Known Activations