© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107176
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those in the context of celebrity culture

    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
    gel
    -0.08
    ERRU
    -0.07
     Gel
    -0.06
    essor
    -0.06
    еб
    -0.06
    eba
    -0.06
    IMA
    -0.06
     Ñģай
    -0.06
    ONES
    -0.06
    kl
    -0.06
    POSITIVE LOGITS
    monster
    0.07
    .yang
    0.07
    anned
    0.07
    adata
    0.07
    ัà¸Ķ
    0.06
    izzato
    0.06
    æª
    0.06
    uche
    0.06
    Å¡ÃŃm
    0.06
     formal
    0.06
    Activations Density 0.001%

    No Known Activations