© 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. 58617
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and their associated timelines

    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
    smith
    -0.08
     addCriterion
    -0.07
    >window
    -0.07
    ãĤ¯ãĤ»
    -0.06
    .TableName
    -0.06
     consect
    -0.06
    å¥
    -0.06
    аÑĢÑĩ
    -0.06
    æĮ¯
    -0.06
    ãĤ¾
    -0.06
    POSITIVE LOGITS
     completion
    0.08
     outcome
    0.07
     forthcoming
    0.07
     pending
    0.07
     completing
    0.07
     upcoming
    0.07
    outcome
    0.07
     finish
    0.07
    859
    0.06
    vest
    0.06
    Activations Density 0.013%

    No Known Activations