© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29766
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software and programming

    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
    Ïĩή
    -0.08
     sublic
    -0.07
    nict
    -0.07
    æ¿ĥ
    -0.07
     plá
    -0.07
    .struts
    -0.07
    vou
    -0.07
    اجات
    -0.07
    AGES
    -0.07
    /UIKit
    -0.07
    POSITIVE LOGITS
    tips
    0.06
     hacking
    0.06
     Hitch
    0.06
    .isPresent
    0.06
    blog
    0.05
     Hess
    0.05
     tips
    0.05
    ably
    0.05
    iate
    0.05
    101
    0.05
    Activations Density 0.023%

    No Known Activations