© 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. 107825
    Prev
    Next
    INDEX
    Explanations

    references to family members' names in an obituary context

    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
    ollen
    -0.07
    resa
    -0.07
    ýn
    -0.07
    ãģŁãģı
    -0.07
    å±±å¸Ĥ
    -0.07
    جÙĨ
    -0.07
    emem
    -0.07
     noh
    -0.07
    丸
    -0.07
    ighted
    -0.06
    POSITIVE LOGITS
    -fontawesome
    0.06
    ////////////////////////////////////////////////////////////////////////////////↵↵
    0.06
    Ľi
    0.06
    WithMany
    0.06
     showModal
    0.06
    ominator
    0.06
    Ī
    0.06
    ãĥ¼ãĥĦ
    0.06
    ollectors
    0.06
    castle
    0.06
    Activations Density 0.012%

    No Known Activations