© 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. 29209
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to work and job performance

    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
    hud
    -0.08
    ilig
    -0.07
    iani
    -0.07
    lesh
    -0.07
    ishi
    -0.07
     chấp
    -0.07
    å·
    -0.07
    itchen
    -0.07
    Æ°á»Łng
    -0.06
    esi
    -0.06
    POSITIVE LOGITS
    elin
    0.07
    ëĮĢë¡ľ
    0.06
     justice
    0.06
     Sutton
    0.06
    ikat
    0.06
    artner
    0.06
    usu
    0.06
     Taylor
    0.06
    ovit
    0.06
    stery
    0.06
    Activations Density 0.011%

    No Known Activations