© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 130100
    Prev
    Next
    INDEX
    Explanations

    themes related to current events and news stories

    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
    rava
    -0.09
     Bunu
    -0.07
    niÄį
    -0.07
     çŁ
    -0.07
    anness
    -0.07
    è´¹ç͍
    -0.07
    çŁ¢
    -0.07
    æ½
    -0.07
    posix
    -0.07
    .nodeType
    -0.07
    POSITIVE LOGITS
     news
    0.12
    news
    0.10
     events
    0.09
     world
    0.08
     global
    0.08
     topics
    0.08
     happening
    0.08
    äºĭä»¶
    0.08
     affairs
    0.08
    -news
    0.08
    Activations Density 0.021%

    No Known Activations