© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57152
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data structures and images in programming contexts

    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
    arge
    -0.07
    Media
    -0.06
    try
    -0.06
    .Flag
    -0.06
    enheim
    -0.06
     Media
    -0.06
     Kov
    -0.06
     Wikip
    -0.06
    olik
    -0.06
    .Media
    -0.06
    POSITIVE LOGITS
    ĮĴ
    0.07
    ocene
    0.07
    TestingModule
    0.06
     VÅ¡
    0.06
     FileMode
    0.06
     each
    0.06
    IMITIVE
    0.06
    çļĨ
    0.06
    ialized
    0.06
     automát
    0.06
    Activations Density 0.018%

    No Known Activations