© 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. 60704
    Prev
    Next
    INDEX
    Explanations

    references to Internet Protocol (IP) versions, specifically IPv4 and IPv6

    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
    oten
    -0.07
    ownik
    -0.07
    -kit
    -0.07
    ÙĬراÙĨ
    -0.06
    isons
    -0.06
    piece
    -0.06
    ima
    -0.06
    å¤ĩ
    -0.06
    846
    -0.06
     jadx
    -0.06
    POSITIVE LOGITS
    ế
    0.07
    /fw
    0.07
    оÑĢо
    0.07
    onal
    0.06
    YG
    0.06
     Restr
    0.06
     Ting
    0.06
     restriction
    0.06
    restriction
    0.06
     rol
    0.06
    Activations Density 0.006%

    No Known Activations