© 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. 88268
    Prev
    Next
    INDEX
    Explanations

    terms related to health impacts and safety concerns

    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
    μί
    -0.07
     ydk
    -0.07
     Peterson
    -0.07
     revers
    -0.07
    rente
    -0.06
    .rar
    -0.06
    inho
    -0.06
    /validation
    -0.06
    andel
    -0.06
    .workflow
    -0.06
    POSITIVE LOGITS
    antha
    0.06
     Organisation
    0.06
    chwitz
    0.06
    à¸Ĭาà¸ķ
    0.06
    imer
    0.06
    illance
    0.06
     peri
    0.06
     Workplace
    0.06
    ihan
    0.06
     nat
    0.06
    Activations Density 0.143%

    No Known Activations