© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4297
    Prev
    Next
    INDEX
    Explanations

    references to international relationships and the involvement of countries within global 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
    ä¸Ģ个人
    -0.08
     anyone
    -0.07
     Scalars
    -0.06
    roti
    -0.06
    ÙĪÛĮÙĦ
    -0.06
     travelling
    -0.06
     thoại
    -0.06
     Fields
    -0.06
    izu
    -0.06
    ioso
    -0.06
    POSITIVE LOGITS
    /entities
    0.08
    unga
    0.08
     fur
    0.08
    è»
    0.07
     currencies
    0.07
    fur
    0.07
     member
    0.07
    RequestMethod
    0.07
    member
    0.07
    antas
    0.07
    Activations Density 0.043%

    No Known Activations