© 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. 41012
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to dark matter physics

    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
     splitted
    -0.09
     bigger
    -0.07
     till
    -0.07
     everybody
    -0.07
    wich
    -0.07
     latest
    -0.07
     «
    -0.07
     stuff
    -0.07
     Ñģ
    -0.06
     lately
    -0.06
    POSITIVE LOGITS
    enson
    0.08
    -esque
    0.08
     whilst
    0.08
     recieved
    0.07
     filetype
    0.07
     attempting
    0.07
     seperate
    0.07
     ÙħÛĮتÙĪاÙĨ
    0.07
     amongst
    0.07
    åºĶå½ĵ
    0.07
    Activations Density 0.320%

    No Known Activations