© 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. 40396
    Prev
    Next
    INDEX
    Explanations

    phrases related to family and personal 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
     Lazar
    -0.06
    HEMA
    -0.06
    onda
    -0.06
    ucht
    -0.06
    Ł
    -0.06
    estre
    -0.06
    olds
    -0.06
     smrt
    -0.06
    ovna
    -0.06
     nackte
    -0.06
    POSITIVE LOGITS
    desk
    0.07
     desk
    0.07
    lien
    0.07
    лиÑĨ
    0.06
     vess
    0.06
    asje
    0.06
     Desk
    0.06
    alte
    0.06
    änder
    0.06
     viewer
    0.06
    Activations Density 0.016%

    No Known Activations