© 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. 86074
    Prev
    Next
    INDEX
    Explanations

    phrases indicating expressions of feelings or opinions

    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
    echa
    -0.08
    bject
    -0.08
    /place
    -0.07
    egrity
    -0.07
    رÛĮÙĤ
    -0.07
    /from
    -0.07
    омен
    -0.07
     åij
    -0.07
    kom
    -0.07
    áºŃp
    -0.06
    POSITIVE LOGITS
     concern
    0.09
    ively
    0.07
    ä¸Ģä¸ĭ
    0.07
     concerns
    0.06
     phen
    0.06
     entr
    0.06
     TI
    0.06
    ģm
    0.06
    ams
    0.06
     Concern
    0.06
    Activations Density 0.009%

    No Known Activations