© 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. 15-LLAMASCOPE-RES-131K
    11. 90719
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and expressions of excitement or shared experiences

    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
     themselves
    -0.08
    benh
    -0.07
    atsby
    -0.07
     outr
    -0.06
     mist
    -0.06
    andes
    -0.06
    ilm
    -0.06
     bình
    -0.06
    aÅŁ
    -0.06
     mutual
    -0.06
    POSITIVE LOGITS
    enstein
    0.06
    orris
    0.06
    isman
    0.06
    KHR
    0.06
    NCY
    0.06
    OKEN
    0.06
    θÏħ
    0.06
    ilden
    0.06
     vidéos
    0.06
    RECT
    0.06
    Activations Density 0.030%

    No Known Activations