© 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. 83739
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the completion or aftermath of events

    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
    ãģĵãĤį
    -0.07
     öden
    -0.07
    aken
    -0.07
    ortality
    -0.07
    minus
    -0.07
     massaggi
    -0.07
    ätze
    -0.07
     enthusi
    -0.07
    ÑĢаÑĩ
    -0.07
    é£Ľ
    -0.07
    POSITIVE LOGITS
    107
    0.06
     promises
    0.06
     less
    0.06
     only
    0.06
    -preview
    0.06
    569
    0.06
     Monad
    0.06
     promised
    0.06
     discovery
    0.05
    839
    0.05
    Activations Density 0.015%

    No Known Activations