© 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. 95051
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their impact on communities

    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
     Neighborhood
    -0.07
    347
    -0.07
    Ñģи
    -0.07
     lately
    -0.07
    ickerView
    -0.07
    tent
    -0.07
     neighbourhood
    -0.06
    trak
    -0.06
    caff
    -0.06
    EMPLARY
    -0.06
    POSITIVE LOGITS
     events
    0.10
     history
    0.10
     story
    0.09
     incident
    0.09
    äºĭ件
    0.08
     event
    0.08
     historical
    0.08
     role
    0.08
     episode
    0.08
     History
    0.08
    Activations Density 0.030%

    No Known Activations