© 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 EvalsExportsinterp-engineNEWAPI 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. 17789
    Prev
    Next
    INDEX
    Explanations

    financial allocations related to education and digital access initiatives

    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
    ÑĢаÑĩ
    -0.07
     backed
    -0.06
     pension
    -0.06
    FTA
    -0.06
     frais
    -0.06
    Ñģл
    -0.06
    eur
    -0.05
    reten
    -0.05
     Pension
    -0.05
     cl
    -0.05
    POSITIVE LOGITS
    ogr
    0.06
    strand
    0.06
     ARP
    0.06
     RAT
    0.06
     Boeh
    0.06
     amounts
    0.06
     stranded
    0.06
    ipse
    0.06
    ogy
    0.06
    Í
    0.06
    Activations Density 0.003%

    No Known Activations