© 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. 119486
    Prev
    Next
    INDEX
    Explanations

    references to costs and expenses related to real estate transactions

    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
    .scalablytyped
    -0.10
     ëĦ¤ìĿ´íĬ¸
    -0.09
    oÄŁ
    -0.08
    ¶Į
    -0.08
    mamak
    -0.08
    _Static
    -0.08
    OutOfRange
    -0.08
    олом
    -0.08
    пÑĢа
    -0.08
    taboola
    -0.08
    POSITIVE LOGITS
    0.08
     patch
    0.06
    dl
    0.06
     tank
    0.06
     Canter
    0.06
    di
    0.06
    wig
    0.06
     spr
    0.06
     har
    0.06
     months
    0.06
    Activations Density 0.001%

    No Known Activations