© 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. 9-LLAMASCOPE-RES-131K
    11. 96516
    Prev
    Next
    INDEX
    Explanations

    references to countries and their names in various contexts

    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
     neutral
    -0.06
     Jo
    -0.05
    âĢ¦↵
    -0.05
    ↵↵
    -0.05
    rij
    -0.05
    lage
    -0.05
     Chic
    -0.05
    iced
    -0.05
     and
    -0.05
     un
    -0.05
    POSITIVE LOGITS
     lyon
    0.08
    å¹²
    0.08
    oppable
    0.08
    wins
    0.08
     vlas
    0.07
    Msp
    0.07
    naÄį
    0.07
    asma
    0.07
    ÛĮدÛĮ
    0.07
    ALSE
    0.07
    Activations Density 0.029%

    No Known Activations