© 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. 75778
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers, particularly dates and statistics

    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
    ÑĥзÑĭ
    -0.08
    ÙĨÙĩ
    -0.08
     [...]↵↵
    -0.08
    еÑĩ
    -0.08
    ìĸ´ëĤĺ
    -0.07
    èŃ·
    -0.07
    itol
    -0.07
    ãĤ¥
    -0.07
    .om
    -0.07
    ãĤ¸ãĤ¢
    -0.07
    POSITIVE LOGITS
    wart
    0.07
     prior
    0.06
     presently
    0.06
     Fant
    0.05
     subject
    0.05
    lett
    0.05
    inta
    0.05
    sv
    0.05
    dana
    0.05
     Advent
    0.05
    Activations Density 0.093%

    No Known Activations