© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 1586
    Prev
    Next
    INDEX
    Explanations

    phrases indicating diplomatic relations or significant meetings between countries

    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
    artner
    -0.07
    resco
    -0.07
    éné
    -0.07
    OOSE
    -0.07
    Ñĥнд
    -0.06
    Authority
    -0.06
    ↵↵
    -0.06
    ulum
    -0.06
    ระ
    -0.06
    lagen
    -0.06
    POSITIVE LOGITS
    oom
    0.07
     condol
    0.06
    سر
    0.06
    eral
    0.06
    /loader
    0.06
    akk
    0.06
     excell
    0.05
     fel
    0.05
     ê²
    0.05
     ÑģоÑģÑĤоÑı
    0.05
    Activations Density 0.025%

    No Known Activations