© 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. 29315
    Prev
    Next
    INDEX
    Explanations

    terms related to end-of-life care and legal implications

    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
    ambi
    -0.07
    tran
    -0.07
    çĤ
    -0.06
    CreatedBy
    -0.06
     globalization
    -0.06
    adge
    -0.06
    .lab
    -0.06
    trak
    -0.06
    ipe
    -0.06
     worlds
    -0.06
    POSITIVE LOGITS
    дÑı
    0.07
    ovel
    0.06
    uyo
    0.06
    vÄĽd
    0.06
    té
    0.06
     Natural
    0.06
     Milo
    0.06
    ebin
    0.06
    incinn
    0.06
    ±Ð¾ÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations