© 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. 58946
    Prev
    Next
    INDEX
    Explanations

    references to death and burial

    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
    aise
    -0.07
    .ylim
    -0.07
     Ø®ÙĪÙĨ
    -0.06
    ToSelector
    -0.06
    ILI
    -0.06
    ëĬ¥
    -0.06
    奴
    -0.06
    awner
    -0.06
    ÙĪÙĤت
    -0.06
    edo
    -0.06
    POSITIVE LOGITS
     victims
    0.07
     fallen
    0.07
     executed
    0.07
     whose
    0.07
     expired
    0.06
    itect
    0.06
     former
    0.06
     communic
    0.06
     foreign
    0.06
    æº
    0.06
    Activations Density 0.024%

    No Known Activations