© 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. 83541
    Prev
    Next
    INDEX
    Explanations

    mentions of months or dates

    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
    ̣
    -0.07
    ela
    -0.07
    [^
    -0.06
    \CMS
    -0.06
     cho
    -0.06
     relative
    -0.06
     amd
    -0.06
    ặn
    -0.06
     overnight
    -0.06
    :init
    -0.06
    POSITIVE LOGITS
    upe
    0.08
    antor
    0.07
    aeper
    0.07
    tuk
    0.07
    ibold
    0.07
    acket
    0.06
    ÃŃna
    0.06
    idor
    0.06
    -transitional
    0.06
    ripp
    0.06
    Activations Density 0.010%

    No Known Activations