© 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. 76418
    Prev
    Next
    INDEX
    Explanations

    details related to health statistics and compliance measures

    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
     Years
    -0.06
    years
    -0.06
    Years
    -0.06
    (TIM
    -0.06
     bedding
    -0.06
     corp
    -0.06
    META
    -0.06
     mutil
    -0.06
     years
    -0.06
     Nordic
    -0.06
    POSITIVE LOGITS
     week
    0.07
    erli
    0.07
    estr
    0.07
     community
    0.07
     Continuing
    0.07
    ãģ®ãģłãĤįãģĨ
    0.06
     fortn
    0.06
     Epidemi
    0.06
    -week
    0.06
    DCALL
    0.06
    Activations Density 0.001%

    No Known Activations