© 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. 16981
    Prev
    Next
    INDEX
    Explanations

    references to notable or hidden items and awards in various 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
    ToDevice
    -0.07
    cene
    -0.06
    832
    -0.06
     famously
    -0.06
     Doub
    -0.06
    SizeMode
    -0.06
    ÐĿЯ
    -0.06
    ence
    -0.06
    дÑı
    -0.06
    ÙĨÙħ
    -0.06
    POSITIVE LOGITS
     overlooked
    0.15
     forgotten
    0.15
     neglected
    0.14
     underrated
    0.13
     ignored
    0.13
     unnoticed
    0.13
     quietly
    0.12
     Forgotten
    0.11
     forgot
    0.11
     hidden
    0.10
    Activations Density 0.130%

    No Known Activations