© 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. 15-LLAMASCOPE-RES-131K
    11. 104475
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and conversational markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Terminal punctuation marks (periods, commas, question marks) appearing at sentence endings or clause boundaries, often in quotation contexts or following proper nouns/specific terms.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Reviewer
    -0.06
    ãĤ
    -0.06
    ãĥ¼ãĥ¬
    -0.06
    è¬
    -0.06
    åľŃ
    -0.06
    avel
    -0.06
    .names
    -0.06
    aviour
    -0.06
    469
    -0.06
     sever
    -0.06
    POSITIVE LOGITS
    143
    0.07
     nar
    0.06
    .SelectedItems
    0.06
    ystore
    0.06
    eller
    0.06
    addle
    0.06
    infinity
    0.06
    ulumi
    0.06
     Specific
    0.06
     Specifically
    0.06
    Activations Density 0.031%

    No Known Activations