© 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. 15-LLAMASCOPE-RES-131K
    6. 27369
    Prev
    Next
    INDEX
    Explanations

    phrases related to preparation and enjoyment of espresso

    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
    sik
    -0.07
    uls
    -0.06
    ulp
    -0.06
    .fs
    -0.06
    otte
    -0.06
    als
    -0.06
    currentColor
    -0.06
    ÑĩÑĥ
    -0.06
    .refs
    -0.06
     View
    -0.05
    POSITIVE LOGITS
    aceae
    0.07
    ERAL
    0.07
    ihn
    0.06
    ãĤ¯ãĥĪ
    0.06
    urance
    0.06
    ìĶ©
    0.06
    .Clone
    0.06
    ERİ
    0.06
     strapon
    0.06
    ancel
    0.06
    Activations Density 0.005%

    No Known Activations