© 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. 58594
    Prev
    Next
    INDEX
    Explanations

    references to demographic changes and migration patterns

    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
    LLU
    -0.08
    azzo
    -0.08
     defaultManager
    -0.08
    otu
    -0.08
    ddit
    -0.08
    hani
    -0.08
    ypical
    -0.07
    JI
    -0.07
     consect
    -0.07
    renom
    -0.07
    POSITIVE LOGITS
     enc
    0.07
     Leaving
    0.07
     em
    0.07
     flight
    0.07
     leaving
    0.06
     move
    0.06
     trend
    0.06
     ex
    0.06
     Leave
    0.06
     rep
    0.06
    Activations Density 0.020%

    No Known Activations