© 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. 120152
    Prev
    Next
    INDEX
    Explanations

    references to cyberattacks and security breaches

    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
    -0.06
    ÑĬ
    -0.06
    anuts
    -0.06
     æIJ
    -0.06
     enqu
    -0.06
    koa
    -0.06
    ï¼ī:
    -0.06
    ÌĢ
    -0.06
    roperties
    -0.06
    ॰
    -0.06
    POSITIVE LOGITS
     tomorrow
    0.07
     tonight
    0.07
    AZY
    0.07
     yesterday
    0.07
     ÑģÑĮогоднÑĸ
    0.06
    ارد
    0.06
    AUDIO
    0.06
    renom
    0.06
    mÃŃt
    0.06
    374
    0.06
    Activations Density 0.018%

    No Known Activations