© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62340
    Prev
    Next
    INDEX
    Explanations

    references to musical works and compositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Date markers, legal citations, and proper nouns in formal historical and bibliographic documents, particularly around WWI-era references and legal cases.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    197
    -0.11
    196
    -0.09
    Û±Û¹Û·
    -0.08
     videot
    -0.08
     vidéos
    -0.07
    errat
    -0.07
     computer
    -0.07
    omm
    -0.07
     video
    -0.07
     tape
    -0.07
    POSITIVE LOGITS
    191
    0.15
    190
    0.14
    189
    0.13
    192
    0.12
    188
    0.12
    187
    0.09
     WW
    0.09
    186
    0.09
     Sphinx
    0.09
    æ³Ĭ
    0.08
    Activations Density 0.812%

    No Known Activations