© 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. 5-LLAMASCOPE-RES-131K
    11. 126829
    Prev
    Next
    INDEX
    Explanations

    references to information resources or data sources

    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
    lie
    -0.07
    nees
    -0.07
    ham
    -0.06
    för
    -0.06
    /or
    -0.06
    asha
    -0.06
     incumbent
    -0.06
    ت
    -0.06
     menstr
    -0.06
    eres
    -0.06
    POSITIVE LOGITS
    оÑģоб
    0.07
    ercial
    0.07
    ëģĶ
    0.07
    relude
    0.07
    desk
    0.07
    .microsoft
    0.07
    yonel
    0.07
    Ń
    0.07
     Plantae
    0.07
    emp
    0.07
    Activations Density 0.009%

    No Known Activations