© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 128911
    Prev
    Next
    INDEX
    Explanations

    the word "aside" and its variations, indicating a focus on supplementary or additional information

    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
    ãģ¾ãģŁ
    -0.07
    rey
    -0.06
    lass
    -0.06
    trap
    -0.06
    ering
    -0.06
    wick
    -0.06
    ses
    -0.06
    drop
    -0.06
    ery
    -0.06
    clus
    -0.06
    POSITIVE LOGITS
     aside
    0.08
    aside
    0.07
    uhe
    0.07
    ëŀĺ
    0.07
    antly
    0.07
    ought
    0.07
    éĢ¸
    0.07
     apart
    0.07
    Ĥæķ°
    0.07
     tieten
    0.07
    Activations Density 0.003%

    No Known Activations