© 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 EvalsExportsinterp-engineNEWAPI 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. 15386
    Prev
    Next
    INDEX
    Explanations

    affirmations or strong confirmations of statements

    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
     знаÑĩиÑĤ
    -0.08
    ãģ¾ãģŁ
    -0.07
    eller
    -0.07
    readcr
    -0.07
    دÛĮگر
    -0.07
    esson
    -0.07
    ediator
    -0.07
    ustral
    -0.07
    election
    -0.07
    ulary
    -0.06
    POSITIVE LOGITS
    zers
    0.07
     most
    0.06
     even
    0.06
    oted
    0.06
    orde
    0.06
    rana
    0.06
     $('#'
    0.06
    once
    0.06
    veloper
    0.05
     almost
    0.05
    Activations Density 0.007%

    No Known Activations