© 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. 5-LLAMASCOPE-RES-131K
    11. 126982
    Prev
    Next
    INDEX
    Explanations

    references to manipulation and exploitation within societal and political contexts

    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
    maz
    -0.07
    zn
    -0.07
    wick
    -0.07
    uitka
    -0.07
    ilan
    -0.06
     å¸Ĥ
    -0.06
    alah
    -0.06
    undy
    -0.06
    اطÙĦ
    -0.06
    xmm
    -0.06
    POSITIVE LOGITS
    Ìģ
    0.06
    -C
    0.06
    .setViewport
    0.06
     satellites
    0.05
    haven
    0.05
    abad
    0.05
    ØŃر
    0.05
     Ald
    0.05
    soever
    0.05
     Arb
    0.05
    Activations Density 0.130%

    No Known Activations