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. 44412
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with the concept of jailbreaking devices, particularly smartphones

    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
    merce
    -0.07
     dilig
    -0.07
    uvo
    -0.07
    浪
    -0.06
     дол
    -0.06
    aliz
    -0.06
    à¸Ķà¸Ļ
    -0.06
    æĶ¯
    -0.06
     Beled
    -0.06
    ẩm
    -0.06
    POSITIVE LOGITS
    break
    0.10
    broken
    0.10
    breaking
    0.10
     jail
    0.10
    unlock
    0.09
     Jail
    0.09
     evasion
    0.09
    hack
    0.09
    breaker
    0.08
    code
    0.08
    Activations Density 0.005%

    No Known Activations