© 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. 61483
    Prev
    Next
    INDEX
    Explanations

    superlative expressions that indicate strong emotional reactions

    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
     controvers
    -0.07
    пÑĢиклад
    -0.07
    contest
    -0.06
     controversial
    -0.06
    opia
    -0.06
    otto
    -0.06
    .Sdk
    -0.06
    @n
    -0.06
     TMPro
    -0.06
     eskort
    -0.06
    POSITIVE LOGITS
    tplib
    0.08
    uncated
    0.08
    generic
    0.07
    .unsplash
    0.06
     amateur
    0.06
     whenever
    0.06
    IALOG
    0.06
     Basic
    0.06
    ãĥĥãĥĹ
    0.06
    IFORM
    0.06
    Activations Density 0.000%

    No Known Activations