© 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. 129580
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical information and associated metadata

    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
     Kens
    -0.07
    urge
    -0.06
    pute
    -0.06
    SENS
    -0.06
    readcr
    -0.06
    ollar
    -0.06
     Flame
    -0.06
     Hung
    -0.06
    atcher
    -0.06
    ertext
    -0.05
    POSITIVE LOGITS
    .jpg
    0.08
    Chip
    0.08
    .png
    0.07
    APPLE
    0.06
    WARDED
    0.06
    QUIRED
    0.06
    _FRONT
    0.06
     Sokol
    0.06
    ARING
    0.06
     ëĵĿ
    0.06
    Activations Density 0.007%

    No Known Activations