© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56574
    Prev
    Next
    INDEX
    Explanations

    HTML or web-related syntax elements, particularly special characters and formatting codes

    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
    ần
    -0.07
    мон
    -0.07
    ahoma
    -0.06
    itel
    -0.06
    utra
    -0.06
    asje
    -0.06
    баÑģ
    -0.06
    ottom
    -0.06
    егоÑĢ
    -0.06
    御
    -0.06
    POSITIVE LOGITS
     Tet
    0.07
    kest
    0.06
    iets
    0.06
    廳
    0.06
     Hubb
    0.06
    kees
    0.06
    cest
    0.06
    OUN
    0.06
    Sea
    0.06
     Demp
    0.06
    Activations Density 0.002%

    No Known Activations