© 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. 89687
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    avr
    -0.07
    ocht
    -0.07
    assium
    -0.07
     Hung
    -0.07
    hoe
    -0.06
    ickle
    -0.06
    outh
    -0.06
    aska
    -0.06
    ãĥ³ãĤ¸
    -0.06
    yang
    -0.06
    POSITIVE LOGITS
    Caption
    0.08
    åĽ
    0.07
     Bernstein
    0.06
    icast
    0.06
    λη
    0.06
    bins
    0.06
    以
    0.06
    oblin
    0.06
     <!--[
    0.05
     chol
    0.05
    Activations Density 0.100%

    No Known Activations