© 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. 40531
    Prev
    Next
    INDEX
    Explanations

    references to migration, asylum-seeking, and safety in the context of refugees

    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
    native
    -0.07
    aln
    -0.07
    ead
    -0.07
    aea
    -0.06
     consort
    -0.06
    heed
    -0.06
    onn
    -0.06
    Progress
    -0.06
    alom
    -0.06
    _FAULT
    -0.06
    POSITIVE LOGITS
     sympathetic
    0.08
     safe
    0.07
    SAFE
    0.07
    моÑĢ
    0.07
     escape
    0.07
     safer
    0.07
     safety
    0.06
    629
    0.06
    safe
    0.06
     nearby
    0.06
    Activations Density 0.021%

    No Known Activations