© 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. 107148
    Prev
    Next
    INDEX
    Explanations

    elements related to death and remembrance

    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
    rego
    -0.06
     pitch
    -0.06
    ilot
    -0.06
    ľ
    -0.06
    itters
    -0.06
    riot
    -0.06
     incoming
    -0.06
    ews
    -0.05
     May
    -0.05
    pitch
    -0.05
    POSITIVE LOGITS
    /Dk
    0.07
    adium
    0.07
    AFX
    0.07
    ÏĥÏĦο
    0.07
    /fontawesome
    0.07
    Ñĸд
    0.07
     Sexo
    0.07
    .gridColumn
    0.06
     Inventory
    0.06
    quential
    0.06
    Activations Density 0.002%

    No Known Activations