© 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. 89266
    Prev
    Next
    INDEX
    Explanations

    negative phrases related to personal accountability and societal expectations

    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
    POCH
    -0.07
     Wilkinson
    -0.07
    IFn
    -0.07
    idlo
    -0.07
     Rut
    -0.07
    à¤ļन
    -0.06
    ahi
    -0.06
    곤
    -0.06
     hereby
    -0.06
    é²ľ
    -0.06
    POSITIVE LOGITS
     toe
    0.08
    ãĥ¼ãĥ³
    0.07
     øns
    0.07
     bow
    0.07
    bows
    0.06
     conform
    0.06
    osen
    0.06
     Lev
    0.06
    ãĥ¼ãĥĢ
    0.06
    jeta
    0.06
    Activations Density 0.039%

    No Known Activations