© 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. 3565
    Prev
    Next
    INDEX
    Explanations

    statistical information related to family and household demographics

    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
    uzey
    -0.08
    NX
    -0.07
    erli
    -0.07
    roys
    -0.06
    ilm
    -0.06
    orgen
    -0.06
     ве
    -0.06
    ilde
    -0.06
    opaque
    -0.06
    getline
    -0.06
    POSITIVE LOGITS
     lone
    0.07
    single
    0.07
    bst
    0.07
     single
    0.06
    .single
    0.06
    /Index
    0.06
     loneliness
    0.06
     оди
    0.06
    åįķ
    0.06
    depend
    0.06
    Activations Density 0.002%

    No Known Activations