© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28748
    Prev
    Next
    INDEX
    Explanations

    references to specific countries or territories, particularly those that include "Liechtenstein" and "Monaco."

    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
    abase
    -0.07
    ointments
    -0.07
    ожеÑĤ
    -0.07
     vyt
    -0.06
    Ñģен
    -0.06
    -selector
    -0.06
    bou
    -0.06
    ucch
    -0.06
    Ñĸка
    -0.06
    oint
    -0.06
    POSITIVE LOGITS
    .mapbox
    0.06
     tiny
    0.06
    um
    0.06
    shire
    0.06
    lue
    0.06
     small
    0.06
    ese
    0.06
     princip
    0.06
     Pis
    0.06
    .camel
    0.06
    Activations Density 0.002%

    No Known Activations