© 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 EvalsExportsinterp-engineNEWAPI 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. 73895
    Prev
    Next
    INDEX
    Explanations

    relationships and connections between individuals

    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
    hea
    -0.07
    osas
    -0.07
    ching
    -0.07
    aldi
    -0.07
    etten
    -0.07
    ürn
    -0.07
    emek
    -0.07
    etÃŃ
    -0.07
    mdir
    -0.07
    eti
    -0.07
    POSITIVE LOGITS
     partner
    0.08
     partners
    0.07
     nem
    0.07
     source
    0.06
    auge
    0.06
     ally
    0.06
     allies
    0.06
     supporters
    0.06
     collabor
    0.06
     coc
    0.06
    Activations Density 0.022%

    No Known Activations