© 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. 5-LLAMASCOPE-RES-131K
    11. 125936
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy independence and grid systems

    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
    coni
    -0.07
    tero
    -0.07
    argent
    -0.07
    âĶĶ
    -0.07
    lez
    -0.07
    ãĥĥãĥģ
    -0.07
     Lat
    -0.07
    astics
    -0.06
    érie
    -0.06
    archy
    -0.06
    POSITIVE LOGITS
    unik
    0.07
    779
    0.06
    isol
    0.06
     side
    0.06
    /on
    0.06
    osal
    0.06
    qa
    0.06
    iman
    0.06
     Side
    0.06
    baar
    0.06
    Activations Density 0.001%

    No Known Activations