© 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 EvalsExportsAPI 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. 77269
    Prev
    Next
    INDEX
    Explanations

    elements related to signals and interrupt handling in programming contexts

    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
    opia
    -0.07
    ighted
    -0.07
    .componentInstance
    -0.06
    ifest
    -0.06
    usercontent
    -0.06
    ewood
    -0.06
    ioxide
    -0.06
    ноÑĩ
    -0.06
    urma
    -0.06
    aggio
    -0.06
    POSITIVE LOGITS
    ustin
    0.06
     wake
    0.06
    CriticalSection
    0.06
     beef
    0.06
    _vect
    0.06
    ä¸ģ
    0.06
    XE
    0.06
    kin
    0.06
    anges
    0.06
     CN
    0.05
    Activations Density 0.012%

    No Known Activations