© 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. 5-LLAMASCOPE-RES-131K
    11. 126979
    Prev
    Next
    INDEX
    Explanations

    mentions of "jelly" and its variations in various 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
     Baker
    -0.06
    ake
    -0.06
    omo
    -0.06
    el
    -0.06
    atte
    -0.05
    anga
    -0.05
     Bake
    -0.05
    ìĶ
    -0.05
    ↵
    -0.05
     stem
    -0.05
    POSITIVE LOGITS
    oard
    0.08
    ìĦľëĬĶ
    0.07
    itou
    0.07
    cilik
    0.07
    ëŀ
    0.07
    ÙĪÙĦÛĮ
    0.07
    bette
    0.07
    è§Ī
    0.07
    buat
    0.07
    alah
    0.07
    Activations Density 0.003%

    No Known Activations