© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 60305
    Prev
    Next
    INDEX
    Explanations

    phrases related to web-based applications and services

    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
    vere
    -0.07
    ookies
    -0.07
    cept
    -0.07
     Luz
    -0.06
    ably
    -0.06
    ookie
    -0.06
    _EXTERN
    -0.06
    jac
    -0.05
    yers
    -0.05
     precision
    -0.05
    POSITIVE LOGITS
    (HTTP
    0.09
    /Web
    0.08
    cob
    0.07
    _traits
    0.07
    cab
    0.07
    /web
    0.07
    erville
    0.07
    .createObject
    0.07
     [=[
    0.07
    sob
    0.07
    Activations Density 0.028%

    No Known Activations