© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125174
    Prev
    Next
    INDEX
    Explanations

    significant events or awards related to community and cultural activities

    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
    amas
    -0.07
    otte
    -0.06
    å±±å¸Ĥ
    -0.06
    inding
    -0.06
    amon
    -0.06
    oru
    -0.06
    idd
    -0.06
     Era
    -0.05
     Funeral
    -0.05
    itou
    -0.05
    POSITIVE LOGITS
     annually
    0.13
     tradition
    0.13
     annual
    0.11
    trad
    0.11
    ä»Ĭå¹´
    0.11
     yearly
    0.11
    annual
    0.10
     Annual
    0.09
    Annual
    0.09
     Tradition
    0.09
    Activations Density 0.061%

    No Known Activations