© 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. 15-LLAMASCOPE-RES-131K
    11. 61416
    Prev
    Next
    INDEX
    Explanations

    themes related to aging and the dynamics of relationships

    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
    entral
    -0.07
    /copyleft
    -0.07
    SSIP
    -0.07
    hsi
    -0.07
    heiro
    -0.07
    onta
    -0.07
    ispers
    -0.07
     kaz
    -0.07
    ĮĴ
    -0.07
    Trade
    -0.07
    POSITIVE LOGITS
     skeletons
    0.06
    ancell
    0.06
     patriarch
    0.06
     family
    0.05
    idir
    0.05
    obia
    0.05
    usra
    0.05
     divisions
    0.05
    eres
    0.05
    iar
    0.05
    Activations Density 0.010%

    No Known Activations