© 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. 39790
    Prev
    Next
    INDEX
    Explanations

    phrases related to various methods or options for transport and logistics

    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
     target
    -0.06
    metic
    -0.06
     targets
    -0.06
    rece
    -0.06
    缮æłĩ
    -0.06
     sobie
    -0.06
    ail
    -0.06
    arefa
    -0.06
     Compilation
    -0.05
    ertz
    -0.05
    POSITIVE LOGITS
     method
    0.13
     ways
    0.11
     methods
    0.10
    æĸ¹å¼ı
    0.10
    method
    0.10
    æĸ¹æ³ķ
    0.10
    _method
    0.10
     way
    0.10
     technique
    0.09
     means
    0.09
    Activations Density 0.063%

    No Known Activations