© 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. 106669
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to identification numbers used for individuals and businesses

    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
    меÑĩ
    -0.06
    udes
    -0.06
    avia
    -0.06
    arro
    -0.06
    aily
    -0.06
    алÑĥ
    -0.06
    ernes
    -0.06
    ouchers
    -0.06
    lyph
    -0.06
     inconvenience
    -0.06
    POSITIVE LOGITS
    needed
    0.07
    oire
    0.07
     business
    0.06
     Sole
    0.06
    elf
    0.06
    åı·
    0.06
     Biz
    0.06
     needed
    0.06
     biz
    0.06
    EZ
    0.06
    Activations Density 0.010%

    No Known Activations