© 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. 29328
    Prev
    Next
    INDEX
    Explanations

    topics related to immigration policies and community impact

    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
    θÏħ
    -0.06
    ignum
    -0.06
     admission
    -0.06
    ft
    -0.06
    DMI
    -0.06
    orno
    -0.06
    roat
    -0.06
    quisition
    -0.06
     society
    -0.05
     nob
    -0.05
    POSITIVE LOGITS
    ieri
    0.08
     ìłĦêµŃ
    0.07
     resource
    0.07
    ëŁ
    0.07
    semblies
    0.07
    cities
    0.07
    eparator
    0.07
    (Resource
    0.07
     RESOURCE
    0.07
    .resource
    0.07
    Activations Density 0.128%

    No Known Activations