© 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. 57872
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in code syntax

    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
    s
    -0.12
    ing
    -0.12
    ãģĦãĤĭ
    -0.10
    Ùĩ
    -0.10
    edl
    -0.09
    tero
    -0.08
    alus
    -0.08
    rganization
    -0.08
    ting
    -0.08
    ska
    -0.07
    POSITIVE LOGITS
    ìĦľëĬĶ
    0.08
    ï¸ı
    0.08
    ìĦľ
    0.07
    vice
    0.07
    ele
    0.07
    inde
    0.07
    ip
    0.07
    eed
    0.07
    theless
    0.07
    mates
    0.07
    Activations Density 0.021%

    No Known Activations