© 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. 15-LLAMASCOPE-RES-131K
    11. 103331
    Prev
    Next
    INDEX
    Explanations

    details about voting laws and regulations

    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
    assis
    -0.07
     SEAL
    -0.06
    uida
    -0.06
    linky
    -0.06
     punch
    -0.06
    ateau
    -0.05
    ä»®
    -0.05
    loat
    -0.05
    plevel
    -0.05
    wil
    -0.05
    POSITIVE LOGITS
    BuilderInterface
    0.07
    одаÑĤелÑĮ
    0.07
    iap
    0.07
    :min
    0.07
    otype
    0.06
    اÙĪت
    0.06
    ãĥ¼ãĥĩ
    0.06
    emi
    0.06
     Flex
    0.06
     state
    0.06
    Activations Density 0.005%

    No Known Activations