© 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. 95137
    Prev
    Next
    INDEX
    Explanations

    phrases indicating focus or orientation towards a specific topic or theme

    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
    mina
    -0.07
    urat
    -0.06
    æ¡
    -0.06
    pf
    -0.06
    âĢĮØ´ÙĨ
    -0.06
     Dün
    -0.06
    asal
    -0.06
    кин
    -0.06
    -translate
    -0.06
    LOUR
    -0.06
    POSITIVE LOGITS
    ness
    0.07
    regor
    0.07
    ettel
    0.07
    ÑĸÑģÑĤÑĮ
    0.07
    xec
    0.07
    engin
    0.07
    rob
    0.06
    NESS
    0.06
    ptron
    0.06
    etsk
    0.06
    Activations Density 0.009%

    No Known Activations