© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 118753
    Prev
    Next
    INDEX
    Explanations

    terms related to the shipping and delivery of items

    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
     front
    -0.06
     liber
    -0.06
    uy
    -0.06
     Front
    -0.06
     penetr
    -0.05
     entry
    -0.05
     lev
    -0.05
     pop
    -0.05
    ayers
    -0.05
     penetration
    -0.05
    POSITIVE LOGITS
    send
    0.08
    åĩºåİ»
    0.08
     DISPATCH
    0.08
    ToDevice
    0.08
    طار
    0.08
    รษ
    0.08
    ereo
    0.08
    utta
    0.08
    -send
    0.07
     kiá»ĩn
    0.07
    Activations Density 0.018%

    No Known Activations