© 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. 71182
    Prev
    Next
    INDEX
    Explanations

    topics related to economic accessibility and consumer behavior

    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
    ucas
    -0.07
    .invoke
    -0.07
    dez
    -0.07
    mey
    -0.07
    ingga
    -0.07
    NgModule
    -0.07
    ftype
    -0.07
    rega
    -0.07
    ADA
    -0.07
    addir
    -0.07
    POSITIVE LOGITS
     possession
    0.10
     households
    0.10
     ownership
    0.09
     household
    0.09
     widespread
    0.08
    æĻ®
    0.08
     owned
    0.07
     everyone
    0.07
     everybody
    0.07
     penetration
    0.07
    Activations Density 0.066%

    No Known Activations