© 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. 15-LLAMASCOPE-RES-131K
    11. 103481
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation marks used in coding or formatting

    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
    iska
    -0.08
    ừa
    -0.06
    lıģına
    -0.06
    irs
    -0.06
    ampa
    -0.06
    usk
    -0.06
    ãĤ¯ãĤ»
    -0.06
    stm
    -0.06
    erties
    -0.06
    ollo
    -0.06
    POSITIVE LOGITS
    ambre
    0.07
    oux
    0.07
     impro
    0.06
    ko
    0.06
    beck
    0.06
    å¼ı
    0.06
     politic
    0.06
    CTR
    0.06
    oran
    0.06
    isex
    0.06
    Activations Density 0.009%

    No Known Activations