© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26783
    Prev
    Next
    INDEX
    Explanations

    references to relationships and emotional 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
    leur
    -0.07
    readcr
    -0.07
    uil
    -0.07
    illez
    -0.07
    aza
    -0.07
    ités
    -0.06
     defa
    -0.06
    ozem
    -0.06
     Fur
    -0.06
    izza
    -0.06
    POSITIVE LOGITS
     encounter
    0.07
     meet
    0.07
     initial
    0.07
     caut
    0.07
    YN
    0.07
     Encounter
    0.06
     incontr
    0.06
     meets
    0.06
    initial
    0.06
    aller
    0.06
    Activations Density 0.024%

    No Known Activations