© 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. 84645
    Prev
    Next
    INDEX
    Explanations

    references to locking mechanisms or synchronization in programming code

    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
    lama
    -0.08
    isson
    -0.08
    lediÄŁi
    -0.07
    leme
    -0.07
    ón
    -0.07
    anton
    -0.07
    iffer
    -0.07
    rtl
    -0.07
    ohan
    -0.07
     trình
    -0.07
    POSITIVE LOGITS
     final
    0.07
    anian
    0.07
    est
    0.06
    IMER
    0.06
    oldem
    0.05
    ìĿ´ê°Ģ
    0.05
    enville
    0.05
     alter
    0.05
     const
    0.05
     Wy
    0.05
    Activations Density 0.001%

    No Known Activations