© 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. 9-LLAMASCOPE-RES-131K
    11. 95912
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a history of accomplishments or achievements

    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
    èĬ
    -0.07
    mey
    -0.07
    awei
    -0.07
    upro
    -0.07
    iyah
    -0.07
    anut
    -0.06
    drž
    -0.06
    ç½®
    -0.06
    ÄįenÃŃ
    -0.06
    genres
    -0.06
    POSITIVE LOGITS
    edly
    0.06
    lane
    0.06
    engo
    0.06
     Guil
    0.06
    ofile
    0.06
    igram
    0.06
    l
    0.06
     history
    0.06
    ategorical
    0.06
     Clayton
    0.06
    Activations Density 0.005%

    No Known Activations