© 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 EvalsExportsinterp-engineNEWAPI 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. 42252
    Prev
    Next
    INDEX
    Explanations

    references to death and loss

    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
    loyd
    -0.07
    ãĥ¼ãĥijãĥ¼
    -0.06
    å¬
    -0.06
     staat
    -0.06
    getApplication
    -0.06
    é¤
    -0.06
     Abort
    -0.06
    .ascii
    -0.06
    ÑĶн
    -0.06
    аÑĤкÑĥ
    -0.06
    POSITIVE LOGITS
     cancer
    0.08
     patriarch
    0.07
     Cancer
    0.07
     died
    0.07
     passed
    0.06
     /*#__
    0.06
    Äįek
    0.06
    kea
    0.06
    _gem
    0.06
     passing
    0.06
    Activations Density 0.013%

    No Known Activations