© 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 EvalsExportsinterp-engineNEWAPI 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. 107573
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant political events and opinions

    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
    .fi
    -0.07
    .listBox
    -0.07
    è©
    -0.07
    íĴĪ
    -0.07
    £p
    -0.07
    /wiki
    -0.07
    fahren
    -0.07
    ζα
    -0.07
    à¥įसर
    -0.07
    552
    -0.07
    POSITIVE LOGITS
     why
    0.09
    .scalablytyped
    0.08
     America
    0.07
    ufen
    0.07
     itemprop
    0.07
     Why
    0.07
     how
    0.07
    stice
    0.06
    apon
    0.06
     lessons
    0.06
    Activations Density 0.024%

    No Known Activations