© 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. 106670
    Prev
    Next
    INDEX
    Explanations

    words related to permissions and legal authorizations

    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
    ugu
    -0.07
    -java
    -0.07
    ibold
    -0.07
    /Foundation
    -0.07
     PureComponent
    -0.07
    edImage
    -0.07
    ileceÄŁini
    -0.07
    ilece
    -0.07
    θεÏģ
    -0.07
    unga
    -0.07
    POSITIVE LOGITS
     use
    0.08
    bie
    0.06
    lah
    0.06
     stra
    0.06
    -AA
    0.06
     only
    0.06
     us
    0.05
    .truth
    0.05
    äch
    0.05
    epad
    0.05
    Activations Density 0.015%

    No Known Activations