© 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. 14830
    Prev
    Next
    INDEX
    Explanations

    themes related to terrorism, ideological conflict, and societal threats

    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
    oren
    -0.07
     ple
    -0.07
    erokee
    -0.07
    ITTLE
    -0.06
    .DOM
    -0.06
     INTERVAL
    -0.06
    sson
    -0.06
    vt
    -0.06
     tub
    -0.06
    ORE
    -0.06
    POSITIVE LOGITS
     dangerous
    0.07
     threats
    0.07
     опаÑģ
    0.07
     threat
    0.07
     à¤ĸतर
    0.07
     forces
    0.07
    ë¹Ļ
    0.07
     dangers
    0.07
     attempt
    0.06
    è¯ķ
    0.06
    Activations Density 0.033%

    No Known Activations