© 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. 15-LLAMASCOPE-RES-131K
    11. 88006
    Prev
    Next
    INDEX
    Explanations

    phrases indicating research findings and studies related to health and medicine

    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
    Ñıг
    -0.07
    avl
    -0.06
    ippi
    -0.06
    á»ķ
    -0.06
    asic
    -0.06
     UObject
    -0.06
    .zero
    -0.06
    129
    -0.06
    iano
    -0.05
    -Ñı
    -0.05
    POSITIVE LOGITS
    okers
    0.08
    -results
    0.07
    /Runtime
    0.07
    oker
    0.07
    angen
    0.07
    adar
    0.06
     Independ
    0.06
     links
    0.06
     results
    0.06
    CLR
    0.06
    Activations Density 0.020%

    No Known Activations