© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 128923
    Prev
    Next
    INDEX
    Explanations

    terms related to romantic 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
    аÑĢÑĩ
    -0.07
    erset
    -0.07
    aci
    -0.07
    /animate
    -0.07
    ofday
    -0.07
     æĢ
    -0.06
    .Err
    -0.06
    celik
    -0.06
    èº
    -0.06
    мÑı
    -0.06
    POSITIVE LOGITS
     heaven
    0.07
    imer
    0.07
    天
    0.06
     destiny
    0.06
    uster
    0.06
     destined
    0.06
     Match
    0.06
     god
    0.06
    indo
    0.06
    ynes
    0.06
    Activations Density 0.002%

    No Known Activations