© 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. 40070
    Prev
    Next
    INDEX
    Explanations

    references to people or entities, specifically focusing on their actions or characteristics

    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
    aud
    -0.06
    nt
    -0.06
     Boyd
    -0.06
    ará
    -0.06
    /ros
    -0.06
     ..."↵↵
    -0.06
    INVALID
    -0.05
     SYN
    -0.05
    ota
    -0.05
    atern
    -0.05
    POSITIVE LOGITS
     nÃło
    0.11
     ÑĢеÑĪ
    0.07
    人ãģĮ
    0.07
    kuk
    0.07
    undos
    0.07
    693
    0.07
    (s
    0.06
     ÑĤакого
    0.06
    653
    0.06
    åĢij
    0.06
    Activations Density 0.027%

    No Known Activations