© 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. 87408
    Prev
    Next
    INDEX
    Explanations

    concepts related to epistemology and interrelations between mental and physical properties

    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
     series
    -0.06
    izo
    -0.06
    ropp
    -0.06
     thought
    -0.06
    ories
    -0.05
     zones
    -0.05
    pq
    -0.05
    enerated
    -0.05
    ness
    -0.05
     âĻ
    -0.05
    POSITIVE LOGITS
    æĸ¹éĿ¢
    0.10
     aspect
    0.10
     Aspect
    0.09
    -wise
    0.09
     wise
    0.09
    aspect
    0.09
    wise
    0.09
    ewise
    0.08
    arial
    0.08
    Aspect
    0.08
    Activations Density 0.114%

    No Known Activations