© 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. 5-LLAMASCOPE-RES-131K
    6. 125839
    Prev
    Next
    INDEX
    Explanations

    opening parentheses and their related usage in text

    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
     convention
    -0.06
    ButtonModule
    -0.06
    uro
    -0.06
    ovo
    -0.06
    icie
    -0.06
    æĺİ
    -0.06
    GetMethod
    -0.06
    stroke
    -0.06
    inn
    -0.06
    TION
    -0.06
    POSITIVE LOGITS
    ako
    0.07
    ÙĪÙĨÛĮ
    0.06
    ë¶ĢíĦ°
    0.06
     kah
    0.06
    ÚĨÛĮ
    0.06
     ëĤ´ëł¤
    0.06
    _softmax
    0.06
    gens
    0.06
    /tab
    0.06
     {{--<
    0.06
    Activations Density 0.003%

    No Known Activations