© 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 EvalsExportsAPI 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. 88742
    Prev
    Next
    INDEX
    Explanations

    references to official visits and speeches related to important events or locations

    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
    raison
    -0.07
    insky
    -0.07
    apore
    -0.07
    cores
    -0.07
    anges
    -0.06
    uttle
    -0.06
    opoulos
    -0.06
    odal
    -0.06
    erged
    -0.06
    воз
    -0.06
    POSITIVE LOGITS
     headquarters
    0.12
     Headquarters
    0.11
     HQ
    0.09
     sede
    0.08
     parliament
    0.07
     Initi
    0.07
    HQ
    0.07
     Parliament
    0.06
    hq
    0.06
     offices
    0.06
    Activations Density 0.055%

    No Known Activations