© 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. 15-LLAMASCOPE-RES-131K
    11. 86019
    Prev
    Next
    INDEX
    Explanations

    comparative phrases emphasizing importance, equality, and skill

    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
    argout
    -0.07
    anca
    -0.07
    iesel
    -0.07
    öyle
    -0.07
    ongan
    -0.07
    ocks
    -0.07
     Allan
    -0.07
     >č↵
    -0.07
    illa
    -0.06
    jong
    -0.06
    POSITIVE LOGITS
     equally
    0.14
     alike
    0.08
     equal
    0.08
     Equ
    0.07
    equ
    0.06
     równ
    0.06
    VF
    0.06
     lẫn
    0.06
    Equ
    0.06
     as
    0.06
    Activations Density 0.022%

    No Known Activations