© 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. 26610
    Prev
    Next
    INDEX
    Explanations

    abstract philosophical concepts related to the nature of reality and existence

    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
    æĭħå½ĵ
    -0.06
    gin
    -0.06
     Maj
    -0.06
    .info
    -0.06
     little
    -0.06
    ارک
    -0.06
     ê±°ìĿĺ
    -0.05
     Daniels
    -0.05
    ³
    -0.05
    info
    -0.05
    POSITIVE LOGITS
    emmel
    0.08
    ä»»ä½ķ
    0.07
    vá
    0.07
    ewn
    0.07
    à¹ĥà¸Ķ
    0.07
    .gf
    0.07
    εκ
    0.07
     Picker
    0.07
     Uhr
    0.06
    ynet
    0.06
    Activations Density 0.023%

    No Known Activations