© 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. 92087
    Prev
    Next
    INDEX
    Explanations

    instances of observing or witnessing experiences and their outcomes

    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
    trak
    -0.07
    LETE
    -0.07
    ãĥ¥ãĥ¼
    -0.07
    reste
    -0.07
     поÑħ
    -0.06
    ekil
    -0.06
     дÑĢÑĥго
    -0.06
    anik
    -0.06
    ainties
    -0.06
    èĥİ
    -0.06
    POSITIVE LOGITS
     reactions
    0.07
     reaction
    0.06
     progress
    0.06
     happy
    0.06
    happy
    0.06
     arac
    0.06
     clients
    0.06
     their
    0.06
    _VENDOR
    0.06
     how
    0.06
    Activations Density 0.017%

    No Known Activations