© 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. 78687
    Prev
    Next
    INDEX
    Explanations

    references to aviation incidents or crashes

    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
    ebek
    -0.09
    .scalablytyped
    -0.09
    processable
    -0.08
    ãĤ¦ãĤ¹
    -0.07
    fila
    -0.07
    dates
    -0.07
    имв
    -0.07
    íĹĮ
    -0.07
    licht
    -0.07
    ãĥ³ãĤº
    -0.07
    POSITIVE LOGITS
    .nih
    0.07
     intest
    0.07
     crash
    0.07
     Pilot
    0.06
     pilot
    0.06
    æĬĺ
    0.06
     Hughes
    0.06
     nose
    0.06
     turb
    0.06
    azu
    0.06
    Activations Density 0.006%

    No Known Activations