© 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. 4267
    Prev
    Next
    INDEX
    Explanations

    themes related to intention and emotional states in narrative contexts

    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
    ora
    -0.06
    rah
    -0.06
    ja
    -0.06
    iga
    -0.06
    uti
    -0.06
    leo
    -0.06
    lever
    -0.06
    ray
    -0.05
    ORA
    -0.05
    onom
    -0.05
    POSITIVE LOGITS
     intended
    0.18
     originally
    0.16
     intention
    0.15
     intentions
    0.15
     intend
    0.15
     intent
    0.14
     planned
    0.13
     intending
    0.13
    Intent
    0.13
     initially
    0.13
    Activations Density 0.076%

    No Known Activations