© 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. 15-LLAMASCOPE-RES-131K
    11. 27698
    Prev
    Next
    INDEX
    Explanations

    instances of being assigned responsibilities or duties

    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
    kla
    -0.07
    зÑĭ
    -0.07
    er
    -0.07
    //{{
    -0.06
    steller
    -0.06
    ặc
    -0.06
    iet
    -0.06
    diet
    -0.06
     goede
    -0.06
    .Ui
    -0.06
    POSITIVE LOGITS
     tasks
    0.08
     task
    0.08
    /lic
    0.07
    upon
    0.07
    .prot
    0.07
    ipher
    0.07
     TASK
    0.07
    itag
    0.07
     Tasks
    0.07
    476
    0.07
    Activations Density 0.005%

    No Known Activations