© 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. 119771
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage alongside sentence structures

    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
     Coul
    -0.06
    ctor
    -0.06
    lev
    -0.06
     Dabei
    -0.06
    ảnh
    -0.06
    ÑĦоÑĢма
    -0.06
    ulu
    -0.06
    LETE
    -0.06
    quila
    -0.06
    _DEV
    -0.06
    POSITIVE LOGITS
     instead
    0.20
    instead
    0.19
     Instead
    0.18
    Instead
    0.18
     nor
    0.14
     Nor
    0.14
     вмеÑģÑĤ
    0.13
     sondern
    0.12
    Nor
    0.11
    nor
    0.11
    Activations Density 0.033%

    No Known Activations