© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26901
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the importance of personal achievement and success

    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
    UBE
    -0.07
    usercontent
    -0.06
    registr
    -0.06
    ylv
    -0.06
     Sword
    -0.05
    uge
    -0.05
    ube
    -0.05
    main
    -0.05
     aspiring
    -0.05
     disappearing
    -0.05
    POSITIVE LOGITS
    /Dk
    0.08
    dech
    0.07
    future
    0.07
     eventually
    0.07
     ultimately
    0.07
    eldo
    0.07
     Morrow
    0.07
    idla
    0.07
    ymax
    0.07
    dzi
    0.07
    Activations Density 0.029%

    No Known Activations