© 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. 17-LLAMASCOPE-RES-131K
    6. 87771
    Prev
    Next
    INDEX
    Explanations

    references to technological products or systems and their functionalities

    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
    ãģĻãģĻ
    -0.08
    नल
    -0.07
    Ñģим
    -0.07
    zet
    -0.07
    iye
    -0.07
    elerik
    -0.07
    vm
    -0.07
    Insets
    -0.07
    nid
    -0.06
    erdem
    -0.06
    POSITIVE LOGITS
    568
    0.07
     a
    0.07
     principle
    0.07
     principles
    0.07
     fewer
    0.07
    çļĦæĺ¯
    0.06
     Principle
    0.06
     itself
    0.06
     пÑĢинÑĨип
    0.06
     mostly
    0.06
    Activations Density 0.027%

    No Known Activations