© 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. 89229
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references related to medical conditions

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

    Punctuation marks (particularly periods and closing parentheses) that appear at the end of sections, paragraphs, or numbered points, often marking transitions between content units in structured texts like religious references, recipes, or educational materials.

    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
    Ø¡
    -0.07
     Ye
    -0.07
     Fav
    -0.07
    w
    -0.06
    dz
    -0.06
    agit
    -0.06
     Cum
    -0.06
    l
    -0.06
    änge
    -0.06
    aison
    -0.06
    POSITIVE LOGITS
    endregion
    0.07
     第äºĮ
    0.07
     second
    0.07
    pushViewController
    0.07
    baru
    0.07
     اÙĦثاÙĨÙĬØ©
    0.06
     SECOND
    0.06
    (second
    0.06
    ols
    0.06
    bsub
    0.06
    Activations Density 0.163%

    No Known Activations