© 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. 56254
    Prev
    Next
    INDEX
    Explanations

    phrases related to causes of death and health statistics

    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
    ãĥªãĥ³ãĤ°
    -0.08
    .setter
    -0.07
    eros
    -0.07
     Hispan
    -0.07
    ota
    -0.07
    amous
    -0.07
    agra
    -0.07
    кеÑĤ
    -0.07
    unden
    -0.07
    agos
    -0.07
    POSITIVE LOGITS
     overall
    0.07
    ÑĢа
    0.06
     suite
    0.06
    tes
    0.06
     Suite
    0.06
    overall
    0.06
     kitt
    0.06
     worldwide
    0.05
    Suite
    0.05
     smart
    0.05
    Activations Density 0.009%

    No Known Activations