© 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. 126719
    Prev
    Next
    INDEX
    Explanations

    language related to job security and economic stability

    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
     addCriterion
    -0.07
    sic
    -0.07
    ks
    -0.07
    .jdesktop
    -0.06
    erli
    -0.06
    scape
    -0.06
     Levine
    -0.06
    OUT
    -0.06
    ills
    -0.06
    ING
    -0.06
    POSITIVE LOGITS
    Configurer
    0.07
    PCI
    0.07
    Bearer
    0.07
    ãĤ¤ãĥ¤
    0.06
    allest
    0.06
    Ø¡
    0.06
    ฯ
    0.06
    rovers
    0.06
    uge
    0.06
    aea
    0.06
    Activations Density 0.079%

    No Known Activations