© 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. 38825
    Prev
    Next
    INDEX
    Explanations

    references to political events and figures associated with security and terrorism

    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
    angkan
    -0.08
    ç³»
    -0.07
     PIXI
    -0.07
    åīĤ
    -0.06
    .onOptionsItemSelected
    -0.06
    .Navigator
    -0.06
    еÑĢк
    -0.06
    Injected
    -0.06
    953
    -0.06
    DialogTitle
    -0.06
    POSITIVE LOGITS
     Benghazi
    0.14
     Libya
    0.08
     Libyan
    0.07
    ilo
    0.07
     Perkins
    0.07
    compound
    0.06
     LGPL
    0.06
     rend
    0.06
    æĸ
    0.06
    Fit
    0.06
    Activations Density 0.011%

    No Known Activations