© 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. 62176
    Prev
    Next
    INDEX
    Explanations

    references to countries and their corresponding policies or social conditions

    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
     Steele
    -0.07
    styleType
    -0.07
    ippy
    -0.07
    çļ
    -0.07
    illance
    -0.06
    "indices
    -0.06
    aeper
    -0.06
    mpar
    -0.06
    ocab
    -0.06
    fillType
    -0.06
    POSITIVE LOGITS
     же
    0.07
    人ãģĮ
    0.07
     efforts
    0.06
    332
    0.06
     officials
    0.06
    uttle
    0.06
    illy
    0.06
    ieee
    0.06
     society
    0.06
    685
    0.06
    Activations Density 0.045%

    No Known Activations