© 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. 15-LLAMASCOPE-RES-131K
    11. 104444
    Prev
    Next
    INDEX
    Explanations

    references to funding initiatives and their impact on projects

    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
     se
    -0.06
     recently
    -0.06
    ba
    -0.06
    used
    -0.06
     currently
    -0.06
     bag
    -0.06
     still
    -0.06
     sports
    -0.06
     usually
    -0.05
     used
    -0.05
    POSITIVE LOGITS
    ersiz
    0.08
     éĬ
    0.08
    defs
    0.08
    _contrib
    0.08
    TAIL
    0.07
    _tF
    0.07
    vál
    0.07
    üme
    0.07
    ãĥ¼ãĥª
    0.07
    ÛĮرÙĩ
    0.07
    Activations Density 0.020%

    No Known Activations