© 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. 117703
    Prev
    Next
    INDEX
    Explanations

    references to events and discussions in a narrative context

    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
     daily
    -0.06
    ucking
    -0.06
    /features
    -0.06
    Wake
    -0.06
    daily
    -0.06
    isz
    -0.06
    -columns
    -0.06
     Mondays
    -0.06
    olle
    -0.05
    onde
    -0.05
    POSITIVE LOGITS
     event
    0.14
     audience
    0.13
     session
    0.12
     attendance
    0.12
     attendees
    0.12
    event
    0.11
     evento
    0.11
     Attend
    0.11
    -event
    0.11
    .event
    0.10
    Activations Density 0.033%

    No Known Activations