© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120891
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usage in textual contexts

    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
    YSTEM
    -0.07
     erotico
    -0.07
    verts
    -0.07
    ANNOT
    -0.07
    herits
    -0.07
    anked
    -0.07
     discrepan
    -0.07
    βά
    -0.07
    æ¶
    -0.07
    hsi
    -0.07
    POSITIVE LOGITS
    dy
    0.07
     already
    0.07
    agan
    0.07
     non
    0.06
    asz
    0.06
     very
    0.06
     shall
    0.06
     now
    0.06
    loo
    0.06
    dden
    0.05
    Activations Density 0.009%

    No Known Activations