© 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. 127848
    Prev
    Next
    INDEX
    Explanations

    guidelines and recommendations for event planning and health safety

    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
    ká
    -0.06
    issen
    -0.06
    دة
    -0.06
    ppt
    -0.05
    нка
    -0.05
     Man
    -0.05
    chat
    -0.05
    quet
    -0.05
    radan
    -0.05
     Ballet
    -0.05
    POSITIVE LOGITS
    /Gate
    0.08
    pecia
    0.07
    ResourceId
    0.07
    hours
    0.07
    ODO
    0.07
     hours
    0.07
    Hours
    0.07
     Hours
    0.07
    .oc
    0.07
    gaard
    0.07
    Activations Density 0.021%

    No Known Activations