© 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. 77381
    Prev
    Next
    INDEX
    Explanations

    references to governance and political processes

    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
    åºŃ
    -0.07
    à¥Ģà¤ķरण
    -0.07
    jian
    -0.07
    arton
    -0.07
    .dirty
    -0.07
    subjects
    -0.07
    ¥¿
    -0.07
    mouth
    -0.07
    ollen
    -0.07
    disposed
    -0.07
    POSITIVE LOGITS
     delegated
    0.12
     delegate
    0.10
     deleg
    0.10
     delegation
    0.10
     someone
    0.08
     appoint
    0.08
     handed
    0.07
     deputy
    0.07
     delegates
    0.07
    Delegate
    0.07
    Activations Density 0.036%

    No Known Activations