© 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. 74257
    Prev
    Next
    INDEX
    Explanations

    segments of text that indicate actions or processes, specifically focusing on writing or creative activities

    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
    ante
    -0.07
     Afterwards
    -0.07
    RITE
    -0.07
     afterwards
    -0.07
     afterward
    -0.06
     thereafter
    -0.06
    ANTE
    -0.06
    lass
    -0.06
    dbg
    -0.06
    aldo
    -0.06
    POSITIVE LOGITS
     hence
    0.12
     therefore
    0.11
     now
    0.10
     so
    0.09
     Therefore
    0.09
     Hence
    0.09
    æīĢ以
    0.09
     Now
    0.08
     daher
    0.08
    -now
    0.08
    Activations Density 0.031%

    No Known Activations