© 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. 61376
    Prev
    Next
    INDEX
    Explanations

    punctuation and its contextual significance

    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
    edin
    -0.07
    os
    -0.06
    Äı
    -0.06
    exion
    -0.06
    anton
    -0.06
     Gos
    -0.06
    zeichnet
    -0.06
    kan
    -0.06
     Newman
    -0.06
     mainland
    -0.06
    POSITIVE LOGITS
     but
    0.13
     nhÆ°ng
    0.11
     BUT
    0.11
     но
    0.09
     maar
    0.09
     But
    0.09
    but
    0.09
    _but
    0.09
     pero
    0.08
     mais
    0.08
    Activations Density 0.028%

    No Known Activations