© 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. 89058
    Prev
    Next
    INDEX
    Explanations

    themes of cultural fascination and human 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
    esseract
    -0.09
    inyin
    -0.08
    adem
    -0.07
    andon
    -0.07
    arkin
    -0.07
    egrated
    -0.07
    edula
    -0.06
    odesk
    -0.06
     EPA
    -0.06
    arket
    -0.06
    POSITIVE LOGITS
     fascination
    0.10
     seem
    0.07
    roi
    0.07
     appeal
    0.07
     why
    0.07
     seems
    0.07
     societies
    0.07
     ourselves
    0.06
     universally
    0.06
     pop
    0.06
    Activations Density 0.036%

    No Known Activations