© 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. 62761
    Prev
    Next
    INDEX
    Explanations

    legislative terms and structures within texts

    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
    parable
    -0.06
    appa
    -0.06
    eam
    -0.06
     pardon
    -0.06
    ai
    -0.06
    ©
    -0.06
    abi
    -0.06
     cir
    -0.06
    roe
    -0.06
    elenium
    -0.05
    POSITIVE LOGITS
    reeNode
    0.07
    Floor
    0.07
    VRT
    0.07
     Dün
    0.07
    stadt
    0.07
    ioni
    0.07
    braco
    0.07
    .ManyToMany
    0.06
    INCLUDED
    0.06
     kostenlose
    0.06
    Activations Density 0.001%

    No Known Activations