© 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. 62263
    Prev
    Next
    INDEX
    Explanations

    patterns or references to academic or research-related URLs and links

    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
    ooter
    -0.06
     Watt
    -0.06
     vý
    -0.06
    volt
    -0.06
    -inverse
    -0.06
     Bureau
    -0.06
    ALA
    -0.05
     enrich
    -0.05
     Rut
    -0.05
     ratt
    -0.05
    POSITIVE LOGITS
    allo
    0.08
    peri
    0.08
    ubar
    0.07
    /umd
    0.07
    uw
    0.07
    bek
    0.07
    curring
    0.07
    ÏĮδ
    0.07
    imals
    0.07
    alars
    0.07
    Activations Density 0.002%

    No Known Activations