Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43625
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and their performance under attack

    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
    æį·
    -0.06
    ģ
    -0.06
    ANGLES
    -0.06
    ÏĢη
    -0.05
    oples
    -0.05
    \widgets
    -0.05
    åIJĮæŃ¥
    -0.05
     Fulton
    -0.05
    áo
    -0.05
    getc
    -0.05
    POSITIVE LOGITS
     Heap
    0.14
     memory
    0.14
     Memory
    0.13
     heap
    0.13
     RAM
    0.13
     HEAP
    0.13
     allocation
    0.12
     MEMORY
    0.12
     allocations
    0.12
    (memory
    0.12
    Activations Density 0.017%

    No Known Activations