© 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. 60463
    Prev
    Next
    INDEX
    Explanations

    references to structured lists or data within text

    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
    rimp
    -0.07
    ↵↵
    -0.06
    @Resource
    -0.06
    ==========↵
    -0.06
    azo
    -0.06
    -gnu
    -0.06
    gue
    -0.06
    unge
    -0.06
    uld
    -0.06
    ä¸Ĭæµ·
    -0.06
    POSITIVE LOGITS
     bý
    0.07
    ãĥįãĥ«
    0.07
    steder
    0.06
    Äįin
    0.06
    Msp
    0.06
    cela
    0.06
    alla
    0.06
     konkrét
    0.06
    åĶ¯ä¸Ģ
    0.06
    alars
    0.06
    Activations Density 0.006%

    No Known Activations