© 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. 106472
    Prev
    Next
    INDEX
    Explanations

    programming keywords related to asynchronous operations

    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
    wire
    -0.09
    .scalablytyped
    -0.09
    åĬ
    -0.08
    nock
    -0.08
    undi
    -0.08
    جر
    -0.07
    ÑĥÑĢÑģ
    -0.07
    翼
    -0.07
    #ad
    -0.07
    koneksi
    -0.07
    POSITIVE LOGITS
     Promise
    0.07
    erin
    0.06
    964
    0.06
    물
    0.06
     Medina
    0.06
    t
    0.05
    ÏĦαν
    0.05
     Kok
    0.05
    999
    0.05
    ê¸Ī
    0.05
    Activations Density 0.002%

    No Known Activations