© 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. 17-LLAMASCOPE-RES-131K
    6. 105858
    Prev
    Next
    INDEX
    Explanations

    modal verbs and auxiliary verbs indicating obligation or past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Function words and auxiliary verbs that form grammatical structures or complete verb phrases in sentences.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    енка
    -0.07
    cela
    -0.07
     meis
    -0.07
    lıģa
    -0.07
    rana
    -0.07
    ossier
    -0.07
    aeda
    -0.07
    dde
    -0.07
    еÑĤиÑĩ
    -0.07
    ÑĬ
    -0.06
    POSITIVE LOGITS
    بÙĪØ§Ø³Ø·Ø©
    0.07
     geschichten
    0.07
    PickerController
    0.06
    .LayoutParams
    0.06
    teenth
    0.06
    ablish
    0.06
    @nate
    0.06
    .scalablytyped
    0.06
    łéϤ
    0.06
    lessly
    0.06
    Activations Density 0.071%

    No Known Activations