© 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. 29909
    Prev
    Next
    INDEX
    Explanations

    intensifiers indicating degrees of quality, quantity, or extent

    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
    Äįel
    -0.09
    jeme
    -0.08
     fitte
    -0.08
     reklam
    -0.08
    -vs
    -0.08
    TestFixture
    -0.08
    iyel
    -0.08
     meiden
    -0.08
     klu
    -0.08
    pear
    -0.08
    POSITIVE LOGITS
    :UITableView
    0.06
    iot
    0.06
    ths
    0.06
    Calibri
    0.06
    inned
    0.06
    .
    0.06
    ÂĿ
    0.05
    asics
    0.05
     whatever
    0.05
    gle
    0.05
    Activations Density 0.010%

    No Known Activations