© 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. 119411
    Prev
    Next
    INDEX
    Explanations

    concepts related to the structure and function of systems in engineering, especially focusing on safety and redundancy

    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
    è¼
    -0.07
     FAQ
    -0.06
     leve
    -0.06
     dilation
    -0.06
    inois
    -0.06
    faq
    -0.06
     IRQ
    -0.06
     elit
    -0.06
     Baton
    -0.06
    /umd
    -0.05
    POSITIVE LOGITS
     cabin
    0.10
     Cabin
    0.10
     cockpit
    0.09
    íķŃ
    0.08
     Airways
    0.08
     aircraft
    0.07
     Airlines
    0.07
     flight
    0.07
     wing
    0.07
    翼
    0.07
    Activations Density 0.026%

    No Known Activations