© 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. 56015
    Prev
    Next
    INDEX
    Explanations

    terms related to cohabitation and partnership dynamics

    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
    ppv
    -0.08
    uien
    -0.08
    atron
    -0.08
    uger
    -0.07
    uto
    -0.07
    rames
    -0.07
    lyph
    -0.07
    ofilm
    -0.07
    nds
    -0.07
    anager
    -0.06
    POSITIVE LOGITS
    ucci
    0.07
     relationship
    0.07
     partners
    0.07
    partner
    0.07
     dur
    0.07
     partnership
    0.06
     Partners
    0.06
     sharing
    0.06
     partner
    0.06
     relationships
    0.06
    Activations Density 0.008%

    No Known Activations