© 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. 57897
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contemplation or consideration of various subjects

    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
    dum
    -0.07
    anel
    -0.07
     everywhere
    -0.07
     both
    -0.07
     både
    -0.06
     cannot
    -0.06
    pear
    -0.06
    ãĤªãĥª
    -0.06
    uman
    -0.06
     Pearson
    -0.06
    POSITIVE LOGITS
    until
    0.07
     anymore
    0.07
     Unless
    0.07
     unless
    0.07
    unless
    0.07
    Until
    0.06
     nor
    0.06
     importance
    0.06
    tee
    0.06
     Until
    0.06
    Activations Density 0.013%

    No Known Activations