© 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. 9-LLAMASCOPE-RES-131K
    11. 97898
    Prev
    Next
    INDEX
    Explanations

    references to international trade and countries involved in import/export activities

    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
    PropTypes
    -0.08
    ãĥ³ãĥĶ
    -0.07
    ongan
    -0.07
     disin
    -0.07
    pell
    -0.07
    PELL
    -0.07
    ungan
    -0.06
    opleft
    -0.06
    ibi
    -0.06
    ÑĤап
    -0.06
    POSITIVE LOGITS
    aday
    0.07
    ô
    0.07
    adem
    0.06
    âm
    0.06
    arken
    0.06
    algo
    0.06
    andler
    0.06
    ITION
    0.06
    dition
    0.06
    одав
    0.06
    Activations Density 0.001%

    No Known Activations