© 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 EvalsExportsinterp-engineNEWAPI 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. 87208
    Prev
    Next
    INDEX
    Explanations

    references to various individuals, groups, or entities involved in social, legal, and corporate 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
    orex
    -0.07
    Ñĥнк
    -0.07
    kil
    -0.07
    kiem
    -0.07
    lient
    -0.07
    annis
    -0.07
     Killing
    -0.07
     nhau
    -0.07
     milfs
    -0.06
     ÙĦد
    -0.06
    POSITIVE LOGITS
     being
    0.15
    being
    0.12
     Being
    0.10
     having
    0.10
    Being
    0.09
     becoming
    0.09
     sendo
    0.09
    被
    0.08
    having
    0.07
     essere
    0.07
    Activations Density 0.150%

    No Known Activations