© 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. 15-LLAMASCOPE-RES-131K
    11. 26764
    Prev
    Next
    INDEX
    Explanations

    aspects related to photography and capturing moments at events

    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
     IG
    -0.06
     nackte
    -0.06
     Feedback
    -0.06
    897
    -0.06
    enco
    -0.06
    .defer
    -0.06
    endon
    -0.05
    éªĮ
    -0.05
    htt
    -0.05
     surface
    -0.05
    POSITIVE LOGITS
     assignment
    0.07
    .EventHandler
    0.07
    _assignment
    0.07
    CJK
    0.07
    å¥Ī
    0.07
     assignments
    0.07
     clic
    0.07
    assignments
    0.07
    heck
    0.07
    omed
    0.07
    Activations Density 0.002%

    No Known Activations