© 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. 108313
    Prev
    Next
    INDEX
    Explanations

    concepts related to mental processes and internal struggles

    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
    ttp
    -0.08
    httpClient
    -0.08
    unkt
    -0.07
    inka
    -0.07
    баÑĩ
    -0.07
    uche
    -0.07
    ToLocal
    -0.07
    imos
    -0.07
    ulse
    -0.07
    kits
    -0.06
    POSITIVE LOGITS
     Thoughts
    0.11
     thoughts
    0.11
    Thought
    0.08
     brain
    0.08
     Brain
    0.07
    udas
    0.07
    thought
    0.07
     ideas
    0.07
     Processor
    0.07
    Cog
    0.07
    Activations Density 0.033%

    No Known Activations