© 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. 118680
    Prev
    Next
    INDEX
    Explanations

    keywords related to awards and achievements in various industries

    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
    abbo
    -0.08
     Fried
    -0.07
    UNET
    -0.07
     ÙģÙĪÙĦ
    -0.07
    .Unity
    -0.07
    AGMA
    -0.07
    wap
    -0.07
    ê²ł
    -0.06
    ober
    -0.06
    vil
    -0.06
    POSITIVE LOGITS
    uliar
    0.07
    ureka
    0.07
    wizard
    0.06
     tert
    0.06
    umba
    0.06
     customer
    0.06
     sw
    0.06
     trục
    0.06
    ylv
    0.06
     Warrior
    0.06
    Activations Density 0.000%

    No Known Activations