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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5447
    Prev
    Next
    INDEX
    Explanations

    elements related to digital formats or technologies

    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
    ÑĤий
    -0.07
    ongyang
    -0.07
    qua
    -0.07
    å¹
    -0.07
     ContentView
    -0.07
    ilip
    -0.07
    emarks
    -0.06
    ô
    -0.06
    éļĨ
    -0.06
    lemn
    -0.06
    POSITIVE LOGITS
     wall
    0.08
    .wall
    0.07
     walls
    0.07
     Russia
    0.07
    .bc
    0.07
    wall
    0.06
     Moscow
    0.06
    Vk
    0.06
     Wall
    0.06
    aly
    0.06
    Activations Density 0.000%

    No Known Activations