© 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. 5-LLAMASCOPE-RES-131K
    11. 126772
    Prev
    Next
    INDEX
    Explanations

    words related to interlocking and connections in a construction context

    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
    ãĥ³ãĥĶ
    -0.07
     Hou
    -0.06
     regard
    -0.06
     поÑĪ
    -0.06
    reau
    -0.06
    developer
    -0.06
    르ê²Į
    -0.06
    @protocol
    -0.06
    une
    -0.06
    å¸ĸ
    -0.06
    POSITIVE LOGITS
    alie
    0.07
    anki
    0.06
     Bark
    0.06
    ingly
    0.06
    ви
    0.06
    -BEGIN
    0.06
    asio
    0.06
    presso
    0.06
    alon
    0.06
     snap
    0.06
    Activations Density 0.001%

    No Known Activations