© 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. 17-LLAMASCOPE-RES-131K
    11. 78877
    Prev
    Next
    INDEX
    Explanations

    titles or names of works, particularly those that are significant or noteworthy

    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
    еÑĢеж
    -0.07
    ÑĢÑĸÑĩ
    -0.07
    á»ĭch
    -0.07
    oster
    -0.06
    esa
    -0.06
    info
    -0.06
    ACHI
    -0.06
    ÙĦØŃ
    -0.06
    нож
    -0.06
    енÑĮÑİ
    -0.06
    POSITIVE LOGITS
     simply
    0.08
    rops
    0.07
     '
    0.07
    ropping
    0.07
     "
    0.07
     differently
    0.07
    -Sah
    0.07
     simplement
    0.07
    ropped
    0.07
    ned
    0.06
    Activations Density 0.013%

    No Known Activations