© 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. 129219
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their relationships with various clients and clients' attributes

    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
    otte
    -0.07
    ogr
    -0.07
    untu
    -0.07
    DDS
    -0.07
    strain
    -0.07
     sticking
    -0.07
    lej
    -0.07
    iker
    -0.07
    acher
    -0.07
    emek
    -0.07
    POSITIVE LOGITS
    clients
    0.07
    ãi
    0.07
     clients
    0.07
    Ùĩد
    0.06
     large
    0.06
     entities
    0.06
     mid
    0.06
    -entity
    0.06
     nas
    0.06
     prominent
    0.06
    Activations Density 0.013%

    No Known Activations