© 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. 82456
    Prev
    Next
    INDEX
    Explanations

    expressions of affection or strong emotional connections

    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
    plural
    -0.07
    lobals
    -0.06
    geh
    -0.06
     then
    -0.06
    igung
    -0.06
    plex
    -0.06
    .setup
    -0.06
    lle
    -0.06
    .Utilities
    -0.06
     Orn
    -0.06
    POSITIVE LOGITS
    {}{↵
    0.07
    اÛĮاÙĨ
    0.06
    ecute
    0.06
     навÑĩ
    0.06
    tones
    0.06
     عÙħÙĦÛĮ
    0.06
    è¾
    0.06
    prung
    0.06
     Slots
    0.06
    ptest
    0.06
    Activations Density 0.000%

    No Known Activations