© 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. 17-LLAMASCOPE-RES-131K
    11. 87123
    Prev
    Next
    INDEX
    Explanations

    terms that indicate comparison or reference to "others" in various 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
     putas
    -0.07
    lee
    -0.05
     (
    -0.05
    rompt
    -0.05
    atio
    -0.05
     Buchanan
    -0.05
    ↵
    -0.05
     [
    -0.05
     controlling
    -0.05
     Booster
    -0.05
    POSITIVE LOGITS
    ebek
    0.09
    siyon
    0.08
    chos
    0.08
    agini
    0.08
    duino
    0.08
    ãģªãģĮ
    0.08
     ì¤ijìļĶíķľ
    0.07
    izzo
    0.07
    uien
    0.07
     important
    0.07
    Activations Density 0.012%

    No Known Activations