© 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. 84076
    Prev
    Next
    INDEX
    Explanations

    expressive language related to personal experiences

    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
    goo
    -0.07
    емон
    -0.06
    aternity
    -0.06
    elm
    -0.06
     ÄĮer
    -0.06
    ÃŃf
    -0.06
     CGRectGet
    -0.06
    .criteria
    -0.06
    CRY
    -0.06
    readcr
    -0.06
    POSITIVE LOGITS
     today
    0.09
     yesterday
    0.09
     tomorrow
    0.09
    today
    0.08
     Today
    0.07
    riday
    0.07
    Today
    0.07
     ÑģегоднÑı
    0.07
    continue
    0.07
    ä»ĬæĹ¥
    0.07
    Activations Density 0.049%

    No Known Activations