© 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. 89165
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals associated with a specific institution or location

    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
    oble
    -0.07
     smr
    -0.07
     peÄį
    -0.07
    ceil
    -0.07
    ô
    -0.07
    mpar
    -0.07
    jis
    -0.07
    implode
    -0.07
     veÄįer
    -0.07
    inspace
    -0.07
    POSITIVE LOGITS
    âĢIJ
    0.07
    295
    0.06
    371
    0.06
    kea
    0.06
    nyder
    0.06
    ÙĦÛĮÙĩ
    0.06
    URRE
    0.05
    itz
    0.05
    âĢij
    0.05
    524
    0.05
    Activations Density 0.017%

    No Known Activations