© 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. 61392
    Prev
    Next
    INDEX
    Explanations

    references to U.S. involvement in foreign political interventions and coups

    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
    andle
    -0.07
    ücken
    -0.07
    coma
    -0.06
     Oswald
    -0.06
     buá»ķi
    -0.05
     Cres
    -0.05
     Perform
    -0.05
     Tube
    -0.05
    ports
    -0.05
    ilight
    -0.05
    POSITIVE LOGITS
    avras
    0.09
    contri
    0.07
    nect
    0.07
    à¸Ĭาà¸ķ
    0.06
    olec
    0.06
    aidu
    0.06
     unpopular
    0.06
    arel
    0.06
    strup
    0.06
    kup
    0.06
    Activations Density 0.028%

    No Known Activations