© 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. 17-LLAMASCOPE-RES-131K
    11. 78694
    Prev
    Next
    INDEX
    Explanations

    references to political processes and amendments

    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
    ninger
    -0.07
    .bridge
    -0.07
    jen
    -0.07
    ovation
    -0.07
     @}
    -0.07
    owied
    -0.07
    ginas
    -0.07
     "%"
    -0.07
    лаÑĩ
    -0.07
    ardin
    -0.06
    POSITIVE LOGITS
    arian
    0.06
    581
    0.06
    EE
    0.06
     Powers
    0.06
    emed
    0.05
     rotating
    0.05
     fitness
    0.05
    upply
    0.05
     Martial
    0.05
     Schwarz
    0.05
    Activations Density 0.002%

    No Known Activations