© 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 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. 130229
    Prev
    Next
    INDEX
    Explanations

    key concepts and terms related to arts, performance, and various forms of media production

    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
     Dep
    -0.06
     Hava
    -0.06
     Humph
    -0.06
    .directory
    -0.06
    textBox
    -0.06
    ackson
    -0.06
     Boeh
    -0.06
    EXTERN
    -0.06
    ÑĪин
    -0.06
    xfd
    -0.06
    POSITIVE LOGITS
     tersebut
    0.09
     itself
    0.09
     nÃły
    0.08
    اÛĮع
    0.07
    zik
    0.07
    aug
    0.07
     αÏħÏĦÏĮ
    0.07
    anon
    0.07
    ronym
    0.06
    emann
    0.06
    Activations Density 0.110%

    No Known Activations