© 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. 3018
    Prev
    Next
    INDEX
    Explanations

    themes related to death and mourning

    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
    ãĥĥãĤ«ãĥ¼
    -0.08
     opendir
    -0.08
    msgs
    -0.07
    _iff
    -0.07
    XmlAttribute
    -0.07
    roje
    -0.07
    maktan
    -0.07
    .mit
    -0.07
    ç´Ķ
    -0.07
    .orientation
    -0.07
    POSITIVE LOGITS
    onen
    0.07
     until
    0.07
     world
    0.06
    磨
    0.06
     cor
    0.06
     since
    0.06
    ion
    0.06
     probing
    0.06
     Seed
    0.06
     Death
    0.05
    Activations Density 0.007%

    No Known Activations