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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87859
    Prev
    Next
    INDEX
    Explanations

    Terms related to lawmaking and political processes

    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
     seedu
    -0.08
    wart
    -0.07
    ibly
    -0.07
    iggins
    -0.07
     Král
    -0.07
    Cancelled
    -0.07
     Strikes
    -0.06
    Warnings
    -0.06
    hind
    -0.06
    ìķ¤
    -0.06
    POSITIVE LOGITS
     passage
    0.07
    вай
    0.07
    lds
    0.07
    ampa
    0.06
    uplic
    0.06
    Tracker
    0.06
     Byron
    0.06
    acci
    0.06
     Local
    0.06
     trackers
    0.06
    Activations Density 0.147%

    No Known Activations