© 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. 22-LLAMASCOPE-RES-131K
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    structural components of sentences, focusing on punctuation and sentence breaks

    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
    Others
    -0.07
    gage
    -0.07
     others
    -0.07
    eli
    -0.06
    olle
    -0.06
    anko
    -0.06
    alytics
    -0.06
    íĨµ
    -0.06
    ylko
    -0.06
     Others
    -0.06
    POSITIVE LOGITS
    raphics
    0.07
    Ðİ
    0.07
    itori
    0.07
    thanks
    0.07
    .WinForms
    0.07
     thanks
    0.07
    beck
    0.07
    ewise
    0.06
     consc
    0.06
    rig
    0.06
    Activations Density 0.002%

    No Known Activations