© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16081
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or concepts centered around "of" relating to various topics

    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
    è¿Ļ个
    -0.07
    Äįan
    -0.06
    ourg
    -0.06
     sắc
    -0.06
    uars
    -0.06
    isches
    -0.06
    onn
    -0.06
    rou
    -0.06
    esson
    -0.06
    411
    -0.06
    POSITIVE LOGITS
     being
    0.08
    oux
    0.07
     sorts
    0.06
    ëĭ´
    0.06
    sak
    0.06
    anes
    0.06
     having
    0.06
    want
    0.06
     mistr
    0.06
    ffen
    0.06
    Activations Density 0.048%

    No Known Activations