© 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. 15-LLAMASCOPE-RES-131K
    6. 104216
    Prev
    Next
    INDEX
    Explanations

    phrases related to website features and user engagement

    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
    ÙĨب
    -0.06
    á»ĩ
    -0.06
    brook
    -0.06
     Filename
    -0.06
    clair
    -0.05
    addon
    -0.05
    /h
    -0.05
    criptor
    -0.05
    veloper
    -0.05
     slack
    -0.05
    POSITIVE LOGITS
    IRT
    0.08
    Href
    0.08
    797
    0.08
    ureau
    0.07
    idata
    0.07
    ÑĸÑħ
    0.07
    emez
    0.07
     onLoad
    0.07
    æĺĩ
    0.07
    eny
    0.07
    Activations Density 0.006%

    No Known Activations