© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126740
    Prev
    Next
    INDEX
    Explanations

    products related to home improvement and cleaning

    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
    unan
    -0.07
    åĴ²
    -0.07
    iffe
    -0.07
    éİ
    -0.07
    QtCore
    -0.06
    ATEST
    -0.06
    extras
    -0.06
     za
    -0.06
    oto
    -0.06
    IFT
    -0.06
    POSITIVE LOGITS
    æĥħ
    0.07
    âĦ¢
    0.06
    axed
    0.06
    âĢª
    0.06
    prü
    0.06
    esser
    0.06
    0.06
    itchens
    0.06
    emoth
    0.06
     Medium
    0.06
    Activations Density 0.123%

    No Known Activations