© 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. 104358
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "able" and its derivatives

    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
    innacle
    -0.07
    arian
    -0.06
    655
    -0.06
    arry
    -0.06
     Zheng
    -0.06
    747
    -0.06
    rr
    -0.06
    ile
    -0.06
    isle
    -0.06
    ntl
    -0.06
    POSITIVE LOGITS
     dav
    0.08
    alker
    0.07
    gesch
    0.07
    вок
    0.06
    ohn
    0.06
     åķ
    0.06
    ìĩ
    0.06
    elson
    0.06
     defa
    0.06
     baÅŁlayan
    0.06
    Activations Density 0.000%

    No Known Activations