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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3459
    Prev
    Next
    INDEX
    Explanations

    instances of gatherings or groups involving families or communities

    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
    okino
    -0.09
    èħ
    -0.08
    .LayoutStyle
    -0.08
     ------>
    -0.08
    оÑģп
    -0.08
    ãģĭãĤı
    -0.08
    .pivot
    -0.07
    ifestyles
    -0.07
    oksen
    -0.07
    лÑıн
    -0.07
    POSITIVE LOGITS
     staff
    0.09
     attend
    0.08
     family
    0.08
     assembled
    0.07
     gathered
    0.07
     surrounding
    0.07
     members
    0.07
     attending
    0.07
     
    0.07
     all
    0.07
    Activations Density 0.061%

    No Known Activations