© 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. 40589
    Prev
    Next
    INDEX
    Explanations

    topics related to energy sources and their environmental impact

    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
    zM
    -0.06
     gating
    -0.06
    reso
    -0.06
     mock
    -0.06
     command
    -0.06
    ais
    -0.06
    mock
    -0.05
    awning
    -0.05
     tac
    -0.05
     Brill
    -0.05
    POSITIVE LOGITS
     formations
    0.08
    iman
    0.08
     depos
    0.07
     Formation
    0.07
     formation
    0.07
     processes
    0.07
    uš
    0.07
    ãģ£ãģ¨
    0.07
    ickle
    0.07
     formed
    0.07
    Activations Density 0.016%

    No Known Activations