© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118236
    Prev
    Next
    INDEX
    Explanations

    references to significant events and transitions in narratives

    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
    ÏĦι
    -0.07
    à¸ĵ
    -0.07
    ewood
    -0.07
    .CopyTo
    -0.07
     occasionally
    -0.07
    ellen
    -0.06
    каж
    -0.06
     кого
    -0.06
    .ibatis
    -0.06
     nackte
    -0.06
    POSITIVE LOGITS
     subsequently
    0.19
     subsequent
    0.19
     soon
    0.18
     immediately
    0.18
     later
    0.17
     shortly
    0.16
     thereafter
    0.15
     then
    0.14
    later
    0.14
    soon
    0.14
    Activations Density 0.206%

    No Known Activations