© 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. 29993
    Prev
    Next
    INDEX
    Explanations

    references to main characters or prominent roles in narratives

    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
    uj
    -0.07
    áp
    -0.07
    arian
    -0.06
    hod
    -0.06
    hel
    -0.06
     Head
    -0.06
    sic
    -0.06
    iken
    -0.06
    ÑĭÑĤ
    -0.06
    strand
    -0.06
    POSITIVE LOGITS
    /main
    0.09
     protagonists
    0.07
     protagonist
    0.07
    /reference
    0.07
    -secondary
    0.07
    ddie
    0.06
    stre
    0.06
    preneur
    0.06
    /background
    0.06
     protagon
    0.06
    Activations Density 0.008%

    No Known Activations