© 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. 120185
    Prev
    Next
    INDEX
    Explanations

    geographical references related to sports figures or athletes

    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
    ikel
    -0.06
    engo
    -0.06
    aton
    -0.06
    ine
    -0.06
     underneath
    -0.06
    agner
    -0.06
     Faul
    -0.06
    akah
    -0.05
    ebi
    -0.05
     RTL
    -0.05
    POSITIVE LOGITS
    ancode
    0.08
    ISR
    0.07
     ÑĩÑĥж
    0.07
    unan
    0.07
    istics
    0.07
    Robot
    0.07
     Republic
    0.06
    ract
    0.06
    äºķ
    0.06
    моÑģ
    0.06
    Activations Density 0.001%

    No Known Activations