© 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. 9-LLAMASCOPE-RES-131K
    11. 96487
    Prev
    Next
    INDEX
    Explanations

    references to programming elements and data structures

    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
    .ud
    -0.07
    cae
    -0.06
    ussy
    -0.06
    лиÑĨ
    -0.06
    kill
    -0.06
    kus
    -0.06
    خش
    -0.06
    ÌĨ
    -0.06
    име
    -0.06
     KeyCode
    -0.06
    POSITIVE LOGITS
    itsu
    0.07
    insula
    0.06
    olin
    0.06
    ichier
    0.06
    ÑĢиÑĩ
    0.06
    729
    0.06
    ]={↵
    0.06
    вÑĸдом
    0.06
     اÙĦأسر
    0.06
    730
    0.06
    Activations Density 0.006%

    No Known Activations