© 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. 73019
    Prev
    Next
    INDEX
    Explanations

    themes of historical acknowledgment and collective memory

    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
    depend
    -0.06
    Advice
    -0.06
     /*!↵
    -0.06
    pone
    -0.06
    idebar
    -0.06
     zd
    -0.06
    -interface
    -0.06
    anko
    -0.06
     Cliff
    -0.06
     Meaning
    -0.05
    POSITIVE LOGITS
     today
    0.08
     era
    0.07
    today
    0.07
     eventual
    0.07
     eventually
    0.07
     story
    0.07
    vana
    0.07
     bitterness
    0.07
     hoje
    0.07
    alon
    0.06
    Activations Density 0.041%

    No Known Activations