© 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. 119769
    Prev
    Next
    INDEX
    Explanations

    keyboard-related commands or shortcuts

    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
    rito
    -0.08
    czy
    -0.07
    otas
    -0.07
    izons
    -0.07
    oS
    -0.07
     ÑĢам
    -0.07
    lisi
    -0.07
    uls
    -0.07
    ué
    -0.07
    INGS
    -0.07
    POSITIVE LOGITS
     cr
    0.06
     lan
    0.06
    ·
    0.06
     wil
    0.06
     Teen
    0.05
     surv
    0.05
     function
    0.05
     Superior
    0.05
     sist
    0.05
     Leon
    0.05
    Activations Density 0.003%

    No Known Activations