© 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. 93582
    Prev
    Next
    INDEX
    Explanations

    references to programming or technical terms related to software and data structures

    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
     lin
    -0.06
    δή
    -0.06
     Han
    -0.06
    tons
    -0.06
    Han
    -0.05
    anges
    -0.05
     BLE
    -0.05
    region
    -0.05
     tý
    -0.05
     пÑĢиг
    -0.05
    POSITIVE LOGITS
    .dtd
    0.08
    icÃŃ
    0.08
    arta
    0.07
    νÏĦ
    0.07
    иÑĨин
    0.07
    LOCKS
    0.07
    iros
    0.07
     DataTypes
    0.07
    ÑĢогÑĢа
    0.06
    .xml
    0.06
    Activations Density 0.003%

    No Known Activations