© 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. 87920
    Prev
    Next
    INDEX
    Explanations

    occurrences of the ampersand symbol "&"

    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
    iglia
    -0.08
    icamente
    -0.07
    lyph
    -0.07
    isce
    -0.07
     ogs
    -0.07
    ousy
    -0.07
    esel
    -0.07
    gende
    -0.07
    ::*
    -0.07
    guard
    -0.07
    POSITIVE LOGITS
     Associates
    0.13
    amp
    0.11
     Sons
    0.11
     Company
    0.10
     amp
    0.09
    Associ
    0.09
     associates
    0.09
     Co
    0.09
     company
    0.09
    Company
    0.09
    Activations Density 0.033%

    No Known Activations