© 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. 9-LLAMASCOPE-RES-131K
    11. 96577
    Prev
    Next
    INDEX
    Explanations

    phrases that involve political critique and economic inequality

    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
    AGO
    -0.08
    аÑĢÑĩ
    -0.08
    ÏģÏİν
    -0.08
    ÙĪÙĤ
    -0.07
    ouch
    -0.07
    olla
    -0.07
    iliz
    -0.07
    campo
    -0.07
    eca
    -0.07
    itches
    -0.07
    POSITIVE LOGITS
     Farrell
    0.06
    Ĺ
    0.06
     Humb
    0.05
     ("
    0.05
     Trent
    0.05
     thanks
    0.05
    æ¹
    0.05
     hard
    0.05
     Ye
    0.05
    ÙĪÙĬر
    0.05
    Activations Density 0.004%

    No Known Activations