© 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. 9-LLAMASCOPE-RES-131K
    11. 98903
    Prev
    Next
    INDEX
    Explanations

    directives related to personal care and preparation requirements

    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
    Ñıж
    -0.07
    ckett
    -0.07
    kee
    -0.07
    ACKET
    -0.07
    883
    -0.06
    زب
    -0.06
     Viewing
    -0.06
    reen
    -0.06
    unker
    -0.06
    acia
    -0.06
    POSITIVE LOGITS
    ãĥ©ãĤ¹
    0.07
    veloper
    0.07
    eq
    0.06
    otes
    0.06
    ogui
    0.06
    gw
    0.06
    eros
    0.06
     whenever
    0.06
    elsing
    0.05
     ÙħÙĨÙĩ
    0.05
    Activations Density 0.085%

    No Known Activations