© 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. 127098
    Prev
    Next
    INDEX
    Explanations

    instances of the word "describe" and its variations, indicating a focus on definitions or explanations

    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
    ÑģÑĤÑĢ
    -0.08
    èn
    -0.07
    eter
    -0.07
    Ñĩе
    -0.07
    aras
    -0.07
    saida
    -0.06
    ares
    -0.06
    pers
    -0.06
    à¯įà®
    -0.06
    iná
    -0.06
    POSITIVE LOGITS
    bable
    0.09
    ively
    0.08
     how
    0.08
    /comment
    0.07
    .Xaml
    0.07
    897
    0.07
    afort
    0.07
    uento
    0.07
    .abstract
    0.07
    /ex
    0.06
    Activations Density 0.038%

    No Known Activations