© 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. 30047
    Prev
    Next
    INDEX
    Explanations

    discussion of political and social issues related to governance and community concerns

    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
    ÄĤ
    -0.08
     ÃĤ
    -0.07
    ÃĤ
    -0.06
     ÃĶ
    -0.06
     paras
    -0.06
     Ole
    -0.06
    Ä
    -0.05
    -c
    -0.05
     vex
    -0.05
    éºĹ
    -0.05
    POSITIVE LOGITS
     Ñĩелов
    0.11
     оÑĢганиза
    0.10
     Ukra
    0.10
     performan
    0.09
     еÑģÑĤе
    0.09
     nues
    0.09
     inclu
    0.09
     ÑģÑĥÑīе
    0.09
     вÑģÑĤÑĢе
    0.09
     каÑĩе
    0.09
    Activations Density 0.153%

    No Known Activations