© 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. 56615
    Prev
    Next
    INDEX
    Explanations

    elements of HTML structure related to chat functionality

    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
    ney
    -0.06
    poster
    -0.06
    IPC
    -0.06
    TypeEnum
    -0.06
    IGIN
    -0.06
    =length
    -0.06
     spike
    -0.06
    ãģ£ãģį
    -0.06
    íĺķ
    -0.06
    l
    -0.06
    POSITIVE LOGITS
    askell
    0.07
    ãĥ¼ãĥŃ
    0.07
    awai
    0.07
    esti
    0.07
    isti
    0.06
    VN
    0.06
    <TKey
    0.06
    otos
    0.06
     Haskell
    0.06
    issan
    0.06
    Activations Density 0.021%

    No Known Activations