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

    Neuronpedia

    Jacobian LensNEW
    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. 118852
    Prev
    Next
    INDEX
    Explanations

    references to political roles and positions

    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
    Ä±ÅŁÄ±k
    -0.07
    amera
    -0.07
    rava
    -0.07
    æ°¸ä¹ħ
    -0.07
    çIJĥ
    -0.06
    thic
    -0.06
    ÌĢ
    -0.06
    geries
    -0.06
    ÑĥÑĪки
    -0.06
     treff
    -0.06
    POSITIVE LOGITS
     cabinet
    0.09
     Cabinet
    0.09
     Prime
    0.08
     Cabinets
    0.08
     ministers
    0.07
     cabinets
    0.07
     Ministers
    0.07
     Minist
    0.07
     ministries
    0.07
     resignation
    0.07
    Activations Density 0.036%

    No Known Activations