© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90217
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its specific institutional or government 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
    ongs
    -0.07
    ért
    -0.07
    ohl
    -0.06
    ople
    -0.06
    udas
    -0.06
    oplast
    -0.06
    bras
    -0.06
    uner
    -0.06
     uncomment
    -0.06
     Clintons
    -0.06
    POSITIVE LOGITS
    maz
    0.07
     tük
    0.07
     Gratuit
    0.07
    EMPLARY
    0.06
    zech
    0.06
    -ÑĤо
    0.06
    (æ°´
    0.06
     ComVisible
    0.06
    abyrinth
    0.06
     Gov
    0.06
    Activations Density 0.016%

    No Known Activations