© 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. 15-LLAMASCOPE-RES-131K
    11. 88571
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming 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
    oux
    -0.07
    nÄĽt
    -0.07
    helm
    -0.07
    (åľŁ
    -0.07
    .logged
    -0.07
    OffsetTable
    -0.07
    yg
    -0.07
    reh
    -0.07
    æ´¥
    -0.07
    sanitize
    -0.07
    POSITIVE LOGITS
     Hist
    0.06
    Į¨
    0.06
     Seminar
    0.06
    imir
    0.06
    arer
    0.05
    zac
    0.05
     Linear
    0.05
    555
    0.05
     legitimately
    0.05
    ioso
    0.05
    Activations Density 0.015%

    No Known Activations