© 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 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. 84374
    Prev
    Next
    INDEX
    Explanations

    expressions indicating frequency or commonality of actions and traits

    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
    /Dk
    -0.07
    minster
    -0.07
    weis
    -0.06
    ventional
    -0.06
    mund
    -0.06
    elsea
    -0.06
    icher
    -0.06
     Flags
    -0.06
    vie
    -0.06
    ione
    -0.06
    POSITIVE LOGITS
     used
    0.08
     associated
    0.07
    .ObjectModel
    0.07
    ÙĦÙĬÙģ
    0.07
    =-=-=-=-=-=-=-=-
    0.07
     bý
    0.06
     accompagn
    0.06
    à§įà¦
    0.06
    -thumbnails
    0.06
     associate
    0.06
    Activations Density 0.032%

    No Known Activations