© 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. 107126
    Prev
    Next
    INDEX
    Explanations

    references to authority and power dynamics in a narrative context

    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
     checks
    -0.07
     Cincinnati
    -0.07
    Ī¬
    -0.06
    gesi
    -0.06
     Checks
    -0.06
    墨
    -0.06
     Harding
    -0.06
    ادÙĦ
    -0.06
    ony
    -0.05
    lda
    -0.05
    POSITIVE LOGITS
     Sacramento
    0.08
     Mold
    0.08
     mold
    0.07
     Romanian
    0.07
    ặn
    0.07
    umat
    0.07
     cá
    0.07
     splitter
    0.07
     Worcester
    0.07
    LEAN
    0.07
    Activations Density 0.173%

    No Known Activations