© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87322
    Prev
    Next
    INDEX
    Explanations

    concepts related to cyber-security and protective measures against attacks

    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
     Uniform
    -0.06
    Uniform
    -0.06
     showers
    -0.06
     twe
    -0.06
     killer
    -0.06
    ases
    -0.06
    038
    -0.06
     Union
    -0.06
    ase
    -0.06
     uniform
    -0.06
    POSITIVE LOGITS
     plant
    0.09
     control
    0.09
    ollower
    0.08
     safety
    0.08
    plant
    0.08
     Controllers
    0.08
     Control
    0.08
     controller
    0.08
    /control
    0.08
     plants
    0.08
    Activations Density 0.105%

    No Known Activations