© 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. 9-LLAMASCOPE-RES-131K
    11. 95643
    Prev
    Next
    INDEX
    Explanations

    terms related to welding and material processing

    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
    /Dk
    -0.09
    /GPL
    -0.07
    allas
    -0.07
     گردÛĮد
    -0.07
    /lg
    -0.07
    AutoSize
    -0.07
    Ģ
    -0.07
    -placeholder
    -0.07
    /Foundation
    -0.07
     Vám
    -0.07
    POSITIVE LOGITS
     Lun
    0.07
    agra
    0.06
    ion
    0.06
    a
    0.06
    ation
    0.06
     method
    0.05
     fixed
    0.05
     Perc
    0.05
    :
    0.05
     Gros
    0.05
    Activations Density 0.017%

    No Known Activations