© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14144
    Prev
    Next
    INDEX
    Explanations

    narrative elements involving dialogue and emotional interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    zig
    -0.08
    oven
    -0.07
    âĢ¦)↵↵
    -0.07
    elper
    -0.07
    hei
    -0.07
    utan
    -0.06
    okt
    -0.06
    unma
    -0.06
    nbsp
    -0.06
    elaide
    -0.06
    POSITIVE LOGITS
     again
    0.06
    â
    0.06
    testdata
    0.06
    -dark
    0.06
     alc
    0.06
     bulk
    0.06
    pone
    0.06
     coc
    0.05
     pseud
    0.05
    -Compatible
    0.05
    Activations Density 0.016%

    No Known Activations