© 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. 17-LLAMASCOPE-RES-131K
    6. 129453
    Prev
    Next
    INDEX
    Explanations

    recurring themes and references to optimization and categorization in processes or systems

    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
     almost
    -0.07
     ander
    -0.06
     ANY
    -0.06
    ãĥªãĥ¼ãĤº
    -0.06
    smarty
    -0.06
    aN
    -0.06
    æºĸ
    -0.06
     anywhere
    -0.06
     LIABLE
    -0.06
     elsewhere
    -0.06
    POSITIVE LOGITS
     expressly
    0.10
    ONLY
    0.09
     explicitly
    0.09
     thôi
    0.08
     those
    0.08
     strictly
    0.08
     seule
    0.08
    éĤ£äºĽ
    0.08
     ÙģÙĤØ·
    0.08
    æīį
    0.08
    Activations Density 0.044%

    No Known Activations