© 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. 15-LLAMASCOPE-RES-131K
    11. 61413
    Prev
    Next
    INDEX
    Explanations

    references to constitutional principles and governmental powers

    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
    esiz
    -0.07
    AlmostEqual
    -0.07
    abant
    -0.06
    inç
    -0.06
    vek
    -0.06
     derec
    -0.06
    otor
    -0.06
    ektor
    -0.06
    eti
    -0.06
     GOODMAN
    -0.06
    POSITIVE LOGITS
    Revenue
    0.07
     powers
    0.07
    Atoms
    0.07
     authority
    0.06
     Pickup
    0.06
     power
    0.06
    елик
    0.06
     tak
    0.06
    power
    0.06
    authority
    0.06
    Activations Density 0.002%

    No Known Activations