© 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. 94326
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a comparison or contrast between different subjects

    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
    amp
    -0.07
    isiyle
    -0.07
    ingly
    -0.06
    useum
    -0.06
    ONO
    -0.06
    éľĢæ±Ĥ
    -0.06
    oppins
    -0.06
     åĿ
    -0.06
    å
    -0.06
    ufen
    -0.06
    POSITIVE LOGITS
    ä»ĵ
    0.07
    ä½łçļĦ
    0.07
     offsetX
    0.06
    ìĿ´ì§Ģ
    0.06
    ॰
    0.06
    DevExpress
    0.06
    ëĬIJ
    0.06
    OKIE
    0.06
     sublic
    0.06
    >>>(
    0.06
    Activations Density 0.009%

    No Known Activations