© 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. 87308
    Prev
    Next
    INDEX
    Explanations

    terms related to political majorities and minorities

    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
    rais
    -0.08
    ian
    -0.07
    ians
    -0.07
    iam
    -0.07
    rai
    -0.07
    asse
    -0.07
    \views
    -0.07
    maf
    -0.07
    orre
    -0.07
    irst
    -0.07
    POSITIVE LOGITS
     of
    0.08
    itarian
    0.08
    /min
    0.07
    /full
    0.07
    -of
    0.06
    /all
    0.06
    570
    0.06
     vote
    0.06
    oft
    0.06
     bulk
    0.06
    Activations Density 0.009%

    No Known Activations