© 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. 72070
    Prev
    Next
    INDEX
    Explanations

    specific characters or symbols, particularly those related to linguistic or dialectal expressions

    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
    combe
    -0.07
    adera
    -0.07
    au
    -0.07
    iegel
    -0.07
    acity
    -0.07
    ews
    -0.07
    beh
    -0.06
    rade
    -0.06
    InterfaceOrientation
    -0.06
     Gül
    -0.06
    POSITIVE LOGITS
    iminal
    0.08
     abstraction
    0.07
    ysis
    0.07
     Dial
    0.07
     di
    0.07
     Di
    0.06
    sled
    0.06
    á»ĩn
    0.06
    lectric
    0.06
    arro
    0.06
    Activations Density 0.020%

    No Known Activations