© 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. 9-LLAMASCOPE-RES-131K
    6. 95420
    Prev
    Next
    INDEX
    Explanations

    references to international law and its implications

    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
    ehen
    -0.06
     rational
    -0.06
    dux
    -0.06
     Geg
    -0.06
    andal
    -0.06
    elon
    -0.06
     Advertisement
    -0.05
    onym
    -0.05
     number
    -0.05
    arme
    -0.05
    POSITIVE LOGITS
    rig
    0.08
    StringEncoding
    0.07
    bounding
    0.07
    ownik
    0.07
    ofil
    0.07
    VarChar
    0.07
    ãĥ¬ãĤ¹
    0.07
    ä¾į
    0.07
    ãĤ«ãĥ¼
    0.07
    Ãłnh
    0.06
    Activations Density 0.004%

    No Known Activations