© 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. 121331
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of influence or leadership in entertainment contexts

    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
    _supp
    -0.07
     driving
    -0.07
    æĿŁ
    -0.07
    Wiki
    -0.07
    minent
    -0.06
     bonded
    -0.06
    foon
    -0.06
    aul
    -0.06
     Driving
    -0.06
    å½¹
    -0.06
    POSITIVE LOGITS
    еÑģÑı
    0.08
     produce
    0.08
     produces
    0.07
    lav
    0.07
    âĨ
    0.07
     producing
    0.07
    arella
    0.07
    produ
    0.06
    <?,
    0.06
    dap
    0.06
    Activations Density 0.033%

    No Known Activations