© 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. 76443
    Prev
    Next
    INDEX
    Explanations

    phrases related to political processes and legal entities

    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
    ibold
    -0.07
     ap
    -0.06
    ist
    -0.06
    emoc
    -0.05
    iko
    -0.05
    idd
    -0.05
    _opts
    -0.05
    fur
    -0.05
     typical
    -0.05
     lag
    -0.05
    POSITIVE LOGITS
     sole
    0.20
    sole
    0.18
     purpose
    0.17
     solely
    0.16
    purpose
    0.15
    Purpose
    0.14
     Purpose
    0.14
     Sole
    0.14
     PURPOSE
    0.12
    缮çļĦ
    0.12
    Activations Density 0.058%

    No Known Activations