© 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. 29892
    Prev
    Next
    INDEX
    Explanations

    instances of personal interactions and relationships with others

    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
    алÑİ
    -0.06
     Washer
    -0.06
    ilers
    -0.06
    ULLET
    -0.06
    821
    -0.06
     Hers
    -0.06
    anian
    -0.06
     zoekt
    -0.05
    rez
    -0.05
     tom
    -0.05
    POSITIVE LOGITS
     accompanying
    0.08
     presente
    0.07
    bes
    0.07
    leyen
    0.07
    ̣
    0.07
     ÙĩÙħراÙĩ
    0.07
     phÃŃa
    0.07
     attending
    0.07
    åł´
    0.07
    leaflet
    0.07
    Activations Density 0.076%

    No Known Activations