© 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. 82416
    Prev
    Next
    INDEX
    Explanations

    connections between different entities or concepts marked by commas

    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
    orum
    -0.08
     itself
    -0.07
    ERG
    -0.07
    ãģĵãģ¡ãĤī
    -0.06
    :\/\/
    -0.06
     nÃło
    -0.06
    impse
    -0.06
    人ãģĮ
    -0.06
    #Region
    -0.06
    itle
    -0.06
    POSITIVE LOGITS
     respectively
    0.25
     respective
    0.17
     alike
    0.16
    åĪĨåĪ«
    0.15
     ê°ģê°ģ
    0.13
     two
    0.13
     ÑģооÑĤвеÑĤ
    0.12
     beiden
    0.11
     both
    0.11
    两个
    0.11
    Activations Density 0.059%

    No Known Activations