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. 31-LLAMASCOPE-RES-131K
    6. 43576
    Prev
    Next
    INDEX
    Explanations

    instructions and requirements for implementing programming interfaces

    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
    segue
    -0.06
    rieve
    -0.06
     postupnÄĽ
    -0.06
     Measure
    -0.06
     minimized
    -0.06
    ÙĪÙĤÙģ
    -0.06
    å±ķ示
    -0.06
    _logs
    -0.06
     showcasing
    -0.06
    aton
    -0.05
    POSITIVE LOGITS
     specify
    0.15
     explicitly
    0.13
    spec
    0.13
     spec
    0.13
     specifies
    0.12
    æĮĩå®ļ
    0.12
     tell
    0.12
     specifying
    0.12
     Specify
    0.11
    Specify
    0.11
    Activations Density 0.053%

    No Known Activations