© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62261
    Prev
    Next
    INDEX
    Explanations

    references to extremist ideologies and their influence on youth recruitment

    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
    ucus
    -0.07
    Fear
    -0.07
    oppel
    -0.07
     Ùħرک
    -0.07
     hạ
    -0.07
    iller
    -0.07
    inesis
    -0.07
    orget
    -0.07
    ác
    -0.07
    posite
    -0.07
    POSITIVE LOGITS
     internet
    0.07
     indo
    0.07
     recruitment
    0.07
     recru
    0.06
    ή
    0.06
     recruiters
    0.06
    ÑĦоÑĢми
    0.06
     predis
    0.06
     growing
    0.06
    (ed
    0.06
    Activations Density 0.013%

    No Known Activations