© 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. 15-LLAMASCOPE-RES-131K
    11. 1048
    Prev
    Next
    INDEX
    Explanations

    elements related to software project setup and build configurations

    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
    ülü
    -0.07
    ords
    -0.07
    yny
    -0.06
     Ryan
    -0.06
     itch
    -0.06
    ìĸ¸
    -0.06
     unh
    -0.05
    addle
    -0.05
     Urs
    -0.05
    orda
    -0.05
    POSITIVE LOGITS
    Occurred
    0.08
    CHAIN
    0.08
    TEGER
    0.08
    ispers
    0.07
     ëĵ¤
    0.07
    ileo
    0.07
    hesion
    0.07
     propor
    0.07
    tica
    0.07
    IXEL
    0.07
    Activations Density 0.008%

    No Known Activations