© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96646
    Prev
    Next
    INDEX
    Explanations

    mentions and variations of regular expressions (regex)

    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
    datagrid
    -0.07
    oom
    -0.07
    سÙĪب
    -0.07
    lake
    -0.06
    gre
    -0.06
    angers
    -0.06
    ETCH
    -0.06
    ñana
    -0.06
    cast
    -0.06
    amic
    -0.06
    POSITIVE LOGITS
    大åħ¨
    0.07
    nova
    0.07
    658
    0.07
    изнеÑģ
    0.07
    nid
    0.07
    δα
    0.06
    ilha
    0.06
    วà¸Ķ
    0.06
    sand
    0.06
    LOPT
    0.06
    Activations Density 0.004%

    No Known Activations