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. 43936
    Prev
    Next
    INDEX
    Explanations

    collective expressions of gratitude and acknowledgment

    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
    XMLElement
    -0.06
    381
    -0.06
     Incontri
    -0.06
    anzi
    -0.06
    agers
    -0.06
    tright
    -0.06
     ogs
    -0.06
    rrha
    -0.05
    κÏħ
    -0.05
     ÙĨØ®
    -0.05
    POSITIVE LOGITS
     would
    0.15
     Would
    0.12
    would
    0.12
     want
    0.12
    ’d
    0.12
    Would
    0.11
     extend
    0.11
     wish
    0.10
    'd
    0.10
    want
    0.09
    Activations Density 0.029%

    No Known Activations