© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 84736
    Prev
    Next
    INDEX
    Explanations

    references to age and the lifespan of individuals

    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
    .scalablytyped
    -0.07
    оÑģÑĤаÑĤ
    -0.07
    antasy
    -0.06
    ادا
    -0.06
    INET
    -0.06
    [$_
    -0.06
    )const
    -0.06
     Retrie
    -0.06
    asl
    -0.06
    æĬķ
    -0.06
    POSITIVE LOGITS
     aged
    0.08
     Interview
    0.07
     longevity
    0.07
    living
    0.07
    onom
    0.07
     age
    0.07
     Guinness
    0.07
     living
    0.07
    upd
    0.06
    agen
    0.06
    Activations Density 0.003%

    No Known Activations