Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5034
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to language comprehension and bilingual experiences

    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
    ض
    -0.06
     Ire
    -0.06
     Ireland
    -0.06
    279
    -0.06
     Dice
    -0.06
    ullet
    -0.06
    825
    -0.06
     Lingu
    -0.06
    á»ĥ
    -0.06
    ÏĨÏħ
    -0.05
    POSITIVE LOGITS
     English
    0.16
    English
    0.15
     Spanish
    0.13
    èĭ±è¯Ń
    0.12
     english
    0.12
     French
    0.11
     Hebrew
    0.11
    english
    0.11
     Arabic
    0.10
    Spanish
    0.10
    Activations Density 0.067%

    No Known Activations