© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90909
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming, specifically in the context of web application security and configuration

    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
    SSI
    -0.08
    tember
    -0.08
    .pipeline
    -0.07
    .usermodel
    -0.06
    odom
    -0.06
    Pipeline
    -0.06
    rox
    -0.06
    út
    -0.06
    ienes
    -0.06
    pine
    -0.06
    POSITIVE LOGITS
     ESL
    0.06
    _tac
    0.06
    345
    0.06
     Lehr
    0.06
    emat
    0.06
    ople
    0.06
     kad
    0.06
    idle
    0.06
    ='".$_
    0.06
     Abb
    0.05
    Activations Density 0.008%

    No Known Activations