© 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. 81164
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes related to scripts and stylesheets

    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
    неÑĤ
    -0.07
    ÙĪدÙĩ
    -0.07
    ords
    -0.07
    iffin
    -0.06
    owie
    -0.06
    ondrous
    -0.06
    ConfigurationException
    -0.06
    ourcem
    -0.06
    erator
    -0.06
    olv
    -0.06
    POSITIVE LOGITS
    /javascript
    0.06
    .bundle
    0.06
    ©
    0.06
    usty
    0.06
    idia
    0.06
    fee
    0.06
    ennen
    0.05
    /on
    0.05
    Campo
    0.05
    abaj
    0.05
    Activations Density 0.002%

    No Known Activations