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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5312
    Prev
    Next
    INDEX
    Explanations

    information regarding travel regulations and visa requirements

    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
     éļ
    -0.07
    åĩ¡
    -0.07
    rott
    -0.07
    оÑĩек
    -0.06
    _accessible
    -0.06
    ÑĪиб
    -0.06
    gin
    -0.06
    MDB
    -0.06
    æĺĩ
    -0.06
    æĻ´
    -0.06
    POSITIVE LOGITS
     stay
    0.09
     Extensions
    0.07
     stays
    0.07
     extensions
    0.07
     grace
    0.07
    WithURL
    0.07
    WithMany
    0.06
     overst
    0.06
     Stay
    0.06
    inspect
    0.06
    Activations Density 0.008%

    No Known Activations