© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 77252
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reported speech or quotations

    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
    473
    -0.07
    ils
    -0.06
     sund
    -0.06
    ish
    -0.06
    lein
    -0.05
     longevity
    -0.05
     t
    -0.05
    QUEST
    -0.05
     u
    -0.05
     Camp
    -0.05
    POSITIVE LOGITS
    ernals
    0.07
    ÏĦηÏĥη
    0.07
     TMPro
    0.07
    arez
    0.07
    ENDOR
    0.07
    eral
    0.07
    riad
    0.07
    EATURE
    0.07
    ternal
    0.07
    ynchron
    0.07
    Activations Density 0.002%

    No Known Activations