© 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. 17-LLAMASCOPE-RES-131K
    11. 75404
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintaining or supporting principles and policies

    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
    nim
    -0.07
    hood
    -0.07
    ì§ĢëıĦ
    -0.07
    zk
    -0.07
    into
    -0.07
    arih
    -0.07
    zet
    -0.06
    isset
    -0.06
    à¥ģà¤Ŀ
    -0.06
    efined
    -0.06
    POSITIVE LOGITS
     standards
    0.09
    /down
    0.09
    ance
    0.09
    ably
    0.08
    posables
    0.08
    .scalablytyped
    0.07
    ping
    0.07
     Standards
    0.07
    edly
    0.07
    stery
    0.07
    Activations Density 0.003%

    No Known Activations