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

    Neuronpedia

    Jacobian LensNEW
    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. 84325
    Prev
    Next
    INDEX
    Explanations

    research objectives and study aims related to health outcomes

    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
    344
    -0.07
    antro
    -0.07
    ancements
    -0.07
     elucid
    -0.06
    acerb
    -0.06
    ENA
    -0.06
    alink
    -0.06
    644
    -0.06
    hiro
    -0.06
    й
    -0.06
    POSITIVE LOGITS
    aler
    0.07
     pragma
    0.07
    unk
    0.07
    éĶ
    0.07
    agara
    0.06
    osy
    0.06
    agged
    0.06
    cher
    0.06
    ckt
    0.06
    ï¸ı
    0.06
    Activations Density 0.014%

    No Known Activations