© 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. 90626
    Prev
    Next
    INDEX
    Explanations

    references to specific historical periods or events

    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
    upy
    -0.07
    jez
    -0.06
    /release
    -0.06
    ippy
    -0.06
    seys
    -0.06
    jen
    -0.06
    innie
    -0.06
    dll
    -0.06
    kinson
    -0.06
    EdgeInsets
    -0.06
    POSITIVE LOGITS
     century
    0.08
     اÙĦÙĤرÙĨ
    0.07
    trand
    0.07
    é¼
    0.07
     stoletÃŃ
    0.07
     decades
    0.07
     centuries
    0.07
     fout
    0.06
    istro
    0.06
    Spl
    0.06
    Activations Density 0.004%

    No Known Activations