© 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. 56760
    Prev
    Next
    INDEX
    Explanations

    specific references to governmental or organizational activities and inquiries

    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
    /Dk
    -0.08
     بÙĪابة
    -0.07
    ç´ł
    -0.07
     nuisance
    -0.07
    itemap
    -0.07
    lander
    -0.07
    ãĥ¼ãĤº
    -0.07
    raphics
    -0.07
    bate
    -0.07
     "[%
    -0.07
    POSITIVE LOGITS
    ky
    0.06
     ÑĤем
    0.06
     Key
    0.05
     ê²
    0.05
    Key
    0.05
     Ú¯ÛĮ
    0.05
     Vig
    0.05
     cost
    0.05
    isky
    0.05
    0.05
    Activations Density 0.006%

    No Known Activations