© 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. 103345
    Prev
    Next
    INDEX
    Explanations

    punctuation and references to online sources, specifically citations

    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
    aliases
    -0.08
    ipay
    -0.07
    igram
    -0.07
    locales
    -0.07
    ripper
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    ább
    -0.07
    ós
    -0.07
    sWith
    -0.06
    anko
    -0.06
    POSITIVE LOGITS
     enc
    0.08
     Enc
    0.07
     cond
    0.06
     hypo
    0.06
    د
    0.06
    c
    0.06
    WER
    0.06
     Plan
    0.06
     enclosure
    0.06
     close
    0.05
    Activations Density 0.004%

    No Known Activations