© 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. 60351
    Prev
    Next
    INDEX
    Explanations

    phrases involving the verb "take" with varying 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
    ding
    -0.07
    жи
    -0.07
     Handy
    -0.07
    ieval
    -0.06
    laden
    -0.06
    dni
    -0.06
    dings
    -0.06
    hic
    -0.06
    emails
    -0.06
    atat
    -0.06
    POSITIVE LOGITS
    ets
    0.08
    OG
    0.07
     addAction
    0.07
     chances
    0.07
    758
    0.06
    گاÙĨ
    0.06
    OI
    0.06
     challenge
    0.06
    adaÅŁ
    0.06
     IDb
    0.06
    Activations Density 0.012%

    No Known Activations