© 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. 5-LLAMASCOPE-RES-131K
    6. 127003
    Prev
    Next
    INDEX
    Explanations

    the word "ever" and its variations, indicating a focus on time or permanence

    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
    анка
    -0.07
    ipur
    -0.07
    IID
    -0.07
    abaj
    -0.07
    ozem
    -0.06
    assic
    -0.06
    hle
    -0.06
    ikal
    -0.06
    using
    -0.06
    .initializeApp
    -0.06
    POSITIVE LOGITS
    eto
    0.07
    ëĬ
    0.07
     Partnership
    0.06
    ino
    0.06
    å¥ĸ
    0.06
    ora
    0.06
     spect
    0.06
    heid
    0.06
    çļĦäºĭ
    0.06
     å¢
    0.06
    Activations Density 0.004%

    No Known Activations