© 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. 77650
    Prev
    Next
    INDEX
    Explanations

    topics related to surveys and discussions about project details

    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
    ÅĻiv
    -0.07
    '=>['
    -0.07
    /bind
    -0.07
    .nodeType
    -0.07
    lernen
    -0.07
    ynom
    -0.07
     Battlefield
    -0.06
    atti
    -0.06
     onto
    -0.06
    keh
    -0.06
    POSITIVE LOGITS
     issues
    0.09
     topics
    0.09
    issues
    0.09
     matters
    0.08
     possibilities
    0.08
     topic
    0.08
     options
    0.07
    342
    0.07
     Topic
    0.07
     amongst
    0.07
    Activations Density 0.055%

    No Known Activations