© 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. 75068
    Prev
    Next
    INDEX
    Explanations

    phrases related to disruption and interference

    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
    bia
    -0.08
    avic
    -0.08
    ChangeEvent
    -0.08
    åĴ¨
    -0.08
    mis
    -0.08
    벤
    -0.08
     semiclass
    -0.08
     DERP
    -0.08
    iá»ĥu
    -0.08
    è¨
    -0.07
    POSITIVE LOGITS
     functioning
    0.08
     normal
    0.08
     processes
    0.07
     activities
    0.07
     efforts
    0.07
     flow
    0.07
     operations
    0.07
     communication
    0.07
     function
    0.07
     ability
    0.07
    Activations Density 0.017%

    No Known Activations