© 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. 74380
    Prev
    Next
    INDEX
    Explanations

    elements related to personalization and custom experiences

    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
     focus
    -0.07
    Focus
    -0.07
     Focus
    -0.07
    ahi
    -0.07
    umed
    -0.07
     Hum
    -0.07
    etic
    -0.07
    _focus
    -0.07
    bourg
    -0.06
    -focus
    -0.06
    POSITIVE LOGITS
     personal
    0.10
     personalize
    0.10
     unique
    0.10
    _unique
    0.09
     personality
    0.09
     uniqueness
    0.09
    personal
    0.09
    unique
    0.09
     uniquely
    0.09
    Ownership
    0.09
    Activations Density 0.017%

    No Known Activations