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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5410
    Prev
    Next
    INDEX
    Explanations

    terms related to social and economic frameworks or institutions

    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
    еÑĢк
    -0.07
    .decorate
    -0.07
    InSeconds
    -0.07
    efon
    -0.07
    FileSync
    -0.07
    ardown
    -0.06
    mts
    -0.06
    uluk
    -0.06
    .AF
    -0.06
     discipline
    -0.06
    POSITIVE LOGITS
     Huck
    0.06
     Wald
    0.06
     Fried
    0.06
     Hund
    0.06
    nen
    0.06
    obot
    0.06
    920
    0.06
     Bishop
    0.05
     gh
    0.05
    ТÐŀ
    0.05
    Activations Density 0.003%

    No Known Activations