© 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. 108052
    Prev
    Next
    INDEX
    Explanations

    phrases that describe national identity and strengths in terms of economic and military power

    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
    aga
    -0.07
    elite
    -0.07
    ÑĤÑı
    -0.06
    aint
    -0.06
    agas
    -0.06
    aku
    -0.06
    icerca
    -0.06
    ickey
    -0.06
    itta
    -0.06
    gren
    -0.06
    POSITIVE LOGITS
    osl
    0.08
     society
    0.08
     societies
    0.07
    Callbacks
    0.07
     Pols
    0.07
    öh
    0.07
     mek
    0.07
     spoleÄįnost
    0.07
    Nation
    0.07
    elik
    0.07
    Activations Density 0.036%

    No Known Activations