© 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. 9-LLAMASCOPE-RES-131K
    11. 97592
    Prev
    Next
    INDEX
    Explanations

    terms related to internet service providers and internet connectivity

    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
    inz
    -0.07
    odon
    -0.07
    UIImagePickerController
    -0.07
    Ø´ÙĪ
    -0.07
    ÑĨÑĮ
    -0.07
    ister
    -0.07
    abra
    -0.07
    lei
    -0.07
    uber
    -0.07
    ocio
    -0.06
    POSITIVE LOGITS
    iel
    0.07
    atcher
    0.07
    /media
    0.06
     Tal
    0.06
    ages
    0.06
     primes
    0.06
    -sup
    0.06
    atism
    0.06
     duplic
    0.05
    oi
    0.05
    Activations Density 0.003%

    No Known Activations