© 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. 84116
    Prev
    Next
    INDEX
    Explanations

    references to committees or organizational structures in a formal context

    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
    avou
    -0.07
    ä¸ŃæĸĩåŃĹå¹ķ
    -0.07
    abad
    -0.07
    วà¸Ķ
    -0.07
    istrovstvÃŃ
    -0.07
     Tin
    -0.06
    itu
    -0.06
    iami
    -0.06
    éĺħ读次æķ°
    -0.06
    .GroupLayout
    -0.06
    POSITIVE LOGITS
     Korea
    0.18
     Korean
    0.17
     Koreans
    0.16
     Seoul
    0.16
     Samsung
    0.11
    .kr
    0.11
     Hyundai
    0.11
     Kim
    0.10
     Je
    0.10
    cheon
    0.10
    Activations Density 0.287%

    No Known Activations