© 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 EvalsExportsinterp-engineNEWAPI 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. 71350
    Prev
    Next
    INDEX
    Explanations

    concepts related to existential thoughts and the nature of human existence

    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
    mind
    -0.06
    afort
    -0.06
     subs
    -0.06
    ynes
    -0.06
     mind
    -0.06
    allery
    -0.06
    tiv
    -0.06
    áp
    -0.06
    kyt
    -0.06
    ixon
    -0.06
    POSITIVE LOGITS
    าà¸ĩ
    0.07
    èµĸ
    0.06
     Bapt
    0.06
     helfen
    0.06
    ÏĥÏĦα
    0.06
    Ìĥ
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    iales
    0.06
     Rider
    0.06
    pagesize
    0.06
    Activations Density 0.012%

    No Known Activations