© 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. 124989
    Prev
    Next
    INDEX
    Explanations

    surnames of notable individuals, particularly relating to the context of familial relationships and personal stories

    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
    .scalablytyped
    -0.09
    serter
    -0.08
    má
    -0.07
    plete
    -0.07
    ÏģοÏĤ
    -0.07
    .VideoCapture
    -0.07
    HIR
    -0.07
    ationship
    -0.07
    .untracked
    -0.07
    pesan
    -0.07
    POSITIVE LOGITS
    shaw
    0.07
    ism
    0.06
    layer
    0.06
    116
    0.06
    embros
    0.06
    192
    0.06
    βά
    0.06
    istol
    0.06
    ellar
    0.06
    itis
    0.06
    Activations Density 0.004%

    No Known Activations