© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71904
    Prev
    Next
    INDEX
    Explanations

    references to transactions or statistics related to sales and pricing

    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
    оÑĢе
    -0.07
    .maps
    -0.07
     Pew
    -0.07
    assen
    -0.06
    ochen
    -0.06
    uno
    -0.06
     Spo
    -0.06
     Leone
    -0.06
    uir
    -0.06
    otu
    -0.06
    POSITIVE LOGITS
    .camel
    0.07
    atra
    0.07
    jc
    0.06
    ÙĪدÛĮ
    0.06
    uzey
    0.06
     cer
    0.06
    Parcel
    0.06
    udit
    0.06
    ymph
    0.06
    agra
    0.06
    Activations Density 0.007%

    No Known Activations