© 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. 1019
    Prev
    Next
    INDEX
    Explanations

    terminology related to waste management and equipment repair services

    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
    ansa
    -0.07
    Neo
    -0.07
     Neo
    -0.07
    BASH
    -0.07
    uzzi
    -0.07
    izza
    -0.07
    agar
    -0.07
     neo
    -0.06
    _via
    -0.06
    otify
    -0.06
    POSITIVE LOGITS
     alike
    0.08
     etc
    0.06
    çŃī
    0.06
    537
    0.06
    ยà¸Ńà¸Ķ
    0.06
     Rowe
    0.06
    #ac
    0.06
     amongst
    0.06
     Iron
    0.06
    iron
    0.05
    Activations Density 0.012%

    No Known Activations