© 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. 17-LLAMASCOPE-RES-131K
    11. 88799
    Prev
    Next
    INDEX
    Explanations

    structures and properties related to mathematical graphs

    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
    angs
    -0.07
    ILT
    -0.07
     Hutch
    -0.07
    ombre
    -0.07
    stor
    -0.06
    üny
    -0.06
    	UObject
    -0.06
    gado
    -0.06
    ÏĦαι
    -0.06
    ilters
    -0.06
    POSITIVE LOGITS
    omite
    0.07
     lab
    0.07
    ock
    0.07
     Set
    0.07
    ocab
    0.06
     Cannon
    0.06
     pool
    0.06
     downloader
    0.06
    ecess
    0.06
    pool
    0.06
    Activations Density 0.113%

    No Known Activations