© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126988
    Prev
    Next
    INDEX
    Explanations

    instances of the word "found" in various contexts

    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
    uci
    -0.07
    ekil
    -0.06
    pto
    -0.06
    kovi
    -0.06
    á»į
    -0.06
     whom
    -0.06
    imenti
    -0.06
    oen
    -0.06
    toi
    -0.06
    telegram
    -0.06
    POSITIVE LOGITS
    bugs
    0.07
    474
    0.07
    ResourceManager
    0.06
    crest
    0.06
    mittel
    0.06
     Wizards
    0.06
    OTES
    0.06
    morgan
    0.06
    ýš
    0.06
     à¹Ĩ
    0.06
    Activations Density 0.014%

    No Known Activations