© 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. 107038
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to chemical reactions and mathematical modeling

    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
    loor
    -0.08
    recursive
    -0.07
    ignon
    -0.06
    amous
    -0.06
     تÙĦ
    -0.06
    _ui
    -0.06
     Pell
    -0.06
    {!!
    -0.06
    llen
    -0.06
    strike
    -0.06
    POSITIVE LOGITS
    anden
    0.08
    igg
    0.07
     landscape
    0.07
    anja
    0.06
     landscapes
    0.06
     escape
    0.06
     saddle
    0.06
    ritis
    0.06
    ordion
    0.06
    ä¸ĺ
    0.06
    Activations Density 0.019%

    No Known Activations