© 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. 55565
    Prev
    Next
    INDEX
    Explanations

    instances of the word "split" in various forms and 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
    ymes
    -0.07
    UNE
    -0.07
    unes
    -0.07
    ë£Į
    -0.06
    hit
    -0.06
    usk
    -0.06
    outh
    -0.06
    es
    -0.06
    erli
    -0.06
    alias
    -0.06
    POSITIVE LOGITS
    ting
    0.15
    TING
    0.10
    tered
    0.10
    éIJĺ
    0.10
    TINGS
    0.08
    .Split
    0.08
    tering
    0.08
    ت
    0.08
    aneous
    0.08
    ter
    0.08
    Activations Density 0.015%

    No Known Activations