© 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. 26549
    Prev
    Next
    INDEX
    Explanations

    significant events or occasions

    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
    /ay
    -0.07
    .Messaging
    -0.07
    rais
    -0.07
    Conversation
    -0.07
     اÙĦØŃدÙĬØ«
    -0.06
    eb
    -0.06
     Brend
    -0.06
    Priv
    -0.06
    _Enc
    -0.06
     ctr
    -0.06
    POSITIVE LOGITS
     ceremony
    0.10
     Ceremony
    0.08
     wedding
    0.07
     ceremonies
    0.07
     Warn
    0.07
     Wedding
    0.06
     aisle
    0.06
     parties
    0.06
    stav
    0.06
    TestFixture
    0.06
    Activations Density 0.042%

    No Known Activations