© 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. 17-LLAMASCOPE-RES-131K
    6. 29795
    Prev
    Next
    INDEX
    Explanations

    references to romantic relationships and feelings of love

    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
    ocab
    -0.09
    uzey
    -0.08
    unts
    -0.08
    ulty
    -0.08
    emann
    -0.08
    oint
    -0.08
    oldown
    -0.08
    .scalablytyped
    -0.07
    hek
    -0.07
    raç
    -0.07
    POSITIVE LOGITS
     him
    0.06
    him
    0.06
    AO
    0.06
     someone
    0.06
     dang
    0.06
     whom
    0.06
     Gamb
    0.06
     afar
    0.05
     fall
    0.05
     himself
    0.05
    Activations Density 0.015%

    No Known Activations