© 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. 118710
    Prev
    Next
    INDEX
    Explanations

    words related to marriage

    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
    wards
    -0.09
    ister
    -0.07
    ISTER
    -0.07
    entes
    -0.06
    sey
    -0.06
    ives
    -0.06
    alto
    -0.06
    ary
    -0.06
    alist
    -0.06
    obo
    -0.06
    POSITIVE LOGITS
    elper
    0.07
    ahl
    0.07
    enstein
    0.07
     EINA
    0.07
     someone
    0.07
    emain
    0.07
     Gri
    0.07
    ék
    0.06
     lẽ
    0.06
    elow
    0.06
    Activations Density 0.007%

    No Known Activations