© 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. 104330
    Prev
    Next
    INDEX
    Explanations

    phrases indicating suitability or adequacy for a specific purpose

    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
    reak
    -0.06
     Succ
    -0.06
    ensch
    -0.06
    鼷
    -0.06
    dle
    -0.06
     Oak
    -0.06
    vos
    -0.06
    hung
    -0.06
    Å¡ek
    -0.06
    öt
    -0.06
    POSITIVE LOGITS
     purposes
    0.09
     needs
    0.08
     purpose
    0.07
     Needs
    0.07
    needs
    0.07
    _requirements
    0.06
     accomplish
    0.06
    Needs
    0.06
     Purpose
    0.06
     Nicholson
    0.06
    Activations Density 0.064%

    No Known Activations