© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60576
    Prev
    Next
    INDEX
    Explanations

    programming-related attributes and methods associated with user interface elements

    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
     lowes
    -0.07
    itler
    -0.07
    ubern
    -0.07
    IVERS
    -0.06
    ONEY
    -0.06
    grunt
    -0.06
    омеÑĢ
    -0.06
    CASCADE
    -0.06
    smarty
    -0.06
    reative
    -0.06
    POSITIVE LOGITS
     false
    0.09
    false
    0.09
    (false
    0.08
    =false
    0.08
    (FALSE
    0.07
     true
    0.07
     FALSE
    0.07
    :boolean
    0.07
    :false
    0.07
    true
    0.07
    Activations Density 0.004%

    No Known Activations