© 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. 59819
    Prev
    Next
    INDEX
    Explanations

    terminology related to education and social commentary

    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
    etc
    -0.06
     etc
    -0.05
    []
    -0.05
    â̦↵
    -0.05
     respectively
    -0.05
    Çİ
    -0.05
     or
    -0.05
    ï¼Ł↵
    -0.05
     next
    -0.05
    aw
    -0.05
    POSITIVE LOGITS
    íĸĪê³ł
    0.10
    .updateDynamic
    0.10
    >NN
    0.09
    ãģĹãģ¦ãģĬãĤĬ
    0.09
     iar
    0.09
    HeaderCode
    0.09
    ìĿ´ë©°
    0.09
    ignKey
    0.09
    ãģĬãĤĬ
    0.09
    erset
    0.08
    Activations Density 0.003%

    No Known Activations