© 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. 105168
    Prev
    Next
    INDEX
    Explanations

    issues related to smart meter programs and their associated problems

    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
     تÙĥÙĬÙĬÙģ
    -0.07
     zp
    -0.07
    offsetof
    -0.07
     hrd
    -0.07
    ãĥŁãĥ¥
    -0.07
    iros
    -0.07
     sleeper
    -0.07
    éIJĺ
    -0.07
     infring
    -0.07
    еÑĢÑĭ
    -0.07
    POSITIVE LOGITS
    aur
    0.09
     system
    0.08
     software
    0.08
     computer
    0.08
    egov
    0.07
    ware
    0.07
    system
    0.07
     Computer
    0.07
     Software
    0.07
     System
    0.06
    Activations Density 0.005%

    No Known Activations