© 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. 103838
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
      ↵
    -0.06
    unte
    -0.06
    â
    -0.06
    elm
    -0.06
    ught
    -0.05
    arga
    -0.05
     reput
    -0.05
    asons
    -0.05
    ole
    -0.05
     />
    -0.05
    POSITIVE LOGITS
    usra
    0.08
    âĢ¦.↵↵
    0.07
    aylight
    0.07
    ;:
    0.07
    égor
    0.07
    æ²¢
    0.07
    ãĥĨãĥ«
    0.07
    ambi
    0.07
    GMT
    0.07
    ATAB
    0.07
    Activations Density 0.107%

    No Known Activations