© 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 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. 126865
    Prev
    Next
    INDEX
    Explanations

    references to familial and social 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
    allon
    -0.08
    οι
    -0.07
    omes
    -0.07
    icher
    -0.07
    ettle
    -0.06
    ivement
    -0.06
    館
    -0.06
    ivy
    -0.06
    egl
    -0.06
    beit
    -0.06
    POSITIVE LOGITS
     gift
    0.08
     recipient
    0.07
     birthdays
    0.07
     recipients
    0.06
    recipient
    0.06
     friend
    0.06
     RECEIVER
    0.06
     gifts
    0.06
     Lair
    0.06
    hard
    0.06
    Activations Density 0.007%

    No Known Activations