© 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. 91542
    Prev
    Next
    INDEX
    Explanations

    repeated references to inclusivity and universality in various contexts

    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
    usch
    -0.07
    iren
    -0.07
    ampa
    -0.07
     stuff
    -0.06
    ovel
    -0.06
    req
    -0.06
    inen
    -0.06
    oret
    -0.06
    ired
    -0.06
     Bard
    -0.05
    POSITIVE LOGITS
    ones
    0.08
     conversations
    0.08
    apore
    0.07
    versations
    0.07
    afa
    0.07
    âĦĸâĦĸ
    0.07
    Thunk
    0.06
     conversation
    0.06
    078
    0.06
    ording
    0.06
    Activations Density 0.032%

    No Known Activations