© 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. 71726
    Prev
    Next
    INDEX
    Explanations

    words indicating capability or ability

    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
     briefed
    -0.06
    ieber
    -0.06
    637
    -0.06
    ester
    -0.06
     Dive
    -0.05
     sur
    -0.05
     Riot
    -0.05
    plete
    -0.05
    ilton
    -0.05
     new
    -0.05
    POSITIVE LOGITS
    åIJįçĦ¡ãģĹ
    0.08
    Threads
    0.08
    forum
    0.08
    ascript
    0.08
    ingroup
    0.08
    neutral
    0.07
    ê·
    0.07
    "profile
    0.07
    welcome
    0.07
    Editing
    0.07
    Activations Density 0.000%

    No Known Activations