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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85836
    Prev
    Next
    INDEX
    Explanations

    phrases directing attention to online sources or information

    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
    utm
    -0.07
    ilon
    -0.06
     Cobb
    -0.06
    pora
    -0.06
    YS
    -0.06
    oni
    -0.06
    ys
    -0.06
     reserves
    -0.06
    Reporter
    -0.06
    ana
    -0.06
    POSITIVE LOGITS
    ä»Ķ
    0.08
    /XMLSchema
    0.07
     closely
    0.07
    emmel
    0.07
    HEMA
    0.07
    -NLS
    0.07
     âĸ²
    0.06
    buz
    0.06
    etchup
    0.06
    Dear
    0.06
    Activations Density 0.009%

    No Known Activations