© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1002
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or strong emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Repeated characters, words, or symbols that create emphasis, express emotion, or represent sounds in text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     thừa
    -0.08
    dda
    -0.08
    ienes
    -0.08
    reesome
    -0.07
    .setRotation
    -0.07
    ức
    -0.07
    .DataVisualization
    -0.07
    LARI
    -0.07
    eview
    -0.07
    ë¡ł
    -0.07
    POSITIVE LOGITS
     Monica
    0.06
    sss
    0.05
    olumn
    0.05
    aal
    0.05
     etc
    0.05
     tap
    0.05
    nds
    0.05
     Meyer
    0.05
    isp
    0.05
     volta
    0.05
    Activations Density 0.027%

    No Known Activations