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

    Neuronpedia

    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. 95439
    Prev
    Next
    INDEX
    Explanations

    pronouns that refer to the second person

    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
     chiếu
    -0.07
    οÏħÏģγ
    -0.07
    eker
    -0.07
    .Apis
    -0.07
    rani
    -0.07
    ripsi
    -0.07
    аÑĢи
    -0.07
    RELATED
    -0.07
    xon
    -0.07
    .readyState
    -0.07
    POSITIVE LOGITS
    atin
    0.07
     Co
    0.07
     Manor
    0.06
    æ§ĺ
    0.05
     Moss
    0.05
     intox
    0.05
     Hood
    0.05
    PT
    0.05
     nov
    0.05
    ething
    0.05
    Activations Density 0.000%

    No Known Activations