© 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. 82870
    Prev
    Next
    INDEX
    Explanations

    elements related to personal 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
    ä¸Ī夫
    -0.10
    ãĥŃãĥ¼
    -0.08
    asics
    -0.08
    implify
    -0.07
    olle
    -0.07
     Husband
    -0.07
     husbands
    -0.07
    vida
    -0.07
    465
    -0.06
     miscar
    -0.06
    POSITIVE LOGITS
    妻
    0.09
     ux
    0.08
     wife
    0.08
     himself
    0.08
     gall
    0.08
     Wife
    0.08
     woo
    0.07
     escort
    0.07
     wives
    0.07
     ejac
    0.07
    Activations Density 0.092%

    No Known Activations