© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    terms related to different types of graphs and data structures

    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
    ingly
    -0.08
    ATEST
    -0.08
    inth
    -0.07
    ÌĨ
    -0.07
    izzare
    -0.07
    ̣
    -0.07
    ceptar
    -0.07
    .cloudflare
    -0.07
    ARGET
    -0.07
    iger
    -0.07
    POSITIVE LOGITS
     âĢı
    0.07
    âĢª
    0.06
     Barney
    0.06
    ona
    0.06
    swire
    0.06
     syndrome
    0.06
     Johnson
    0.06
    DataTask
    0.05
    lico
    0.05
    âĦ¢
    0.05
    Activations Density 0.484%

    No Known Activations