© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118129
    Prev
    Next
    INDEX
    Explanations

    words related to family and hierarchical relationships

    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
     Opport
    -0.07
    ottle
    -0.07
    zcze
    -0.07
    sha
    -0.06
    ople
    -0.06
    isko
    -0.06
    ersiz
    -0.06
    esar
    -0.06
    ENCE
    -0.06
    681
    -0.06
    POSITIVE LOGITS
    çļĦæĺ¯
    0.14
     include
    0.09
     consist
    0.09
     عبارت
    0.08
    å°±æĺ¯
    0.08
     consists
    0.08
    ë¡ľëĬĶ
    0.07
     Include
    0.07
     consisted
    0.07
    ãģ®ãģ¯
    0.07
    Activations Density 0.001%

    No Known Activations