© 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. 3289
    Prev
    Next
    INDEX
    Explanations

    phrases indicating processes and actions taken during a task or project

    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
    æĴ
    -0.08
    QRS
    -0.07
    anches
    -0.07
    ateria
    -0.07
    zza
    -0.07
    iani
    -0.07
    gate
    -0.06
    jam
    -0.06
    éł¼
    -0.06
    vr
    -0.06
    POSITIVE LOGITS
    ervo
    0.07
    asar
    0.07
     dry
    0.07
     blond
    0.06
     sty
    0.06
     prepare
    0.06
     Dry
    0.06
     ë§ŀ
    0.06
     Millenn
    0.06
    è¥
    0.06
    Activations Density 0.002%

    No Known Activations