© 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. 74458
    Prev
    Next
    INDEX
    Explanations

    terms related to building and maintaining relationships and connections

    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
    ewise
    -0.07
    duck
    -0.07
    /dc
    -0.07
    CLUDING
    -0.07
    ordin
    -0.07
    ardi
    -0.07
    dez
    -0.06
    /Index
    -0.06
    uide
    -0.06
    quier
    -0.06
    POSITIVE LOGITS
     networks
    0.08
     relationships
    0.07
     connections
    0.07
     Networks
    0.06
     network
    0.06
     among
    0.06
    enc
    0.06
     contacts
    0.06
    relationships
    0.06
    connections
    0.06
    Activations Density 0.018%

    No Known Activations