© 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. 16766
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to government and formal policies

    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
    大人
    -0.08
    opper
    -0.06
    erk
    -0.06
    .land
    -0.06
    egend
    -0.06
    ấp
    -0.06
    uve
    -0.06
    amac
    -0.06
    ushman
    -0.06
    ÛĮدÛĮ
    -0.06
    POSITIVE LOGITS
    utzer
    0.07
    uncio
    0.07
     prom
    0.06
    CTRL
    0.06
     introdu
    0.06
    ä¸
    0.05
     Anime
    0.05
    ÑģÑĮко
    0.05
     invent
    0.05
     Zy
    0.05
    Activations Density 0.001%

    No Known Activations