© 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. 40599
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions or behaviors

    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
    eam
    -0.07
    ACL
    -0.07
    mpr
    -0.07
    icode
    -0.06
    queued
    -0.06
    ï¼»
    -0.06
    ldr
    -0.06
    oku
    -0.06
    анка
    -0.06
     lesbian
    -0.06
    POSITIVE LOGITS
     Trump
    0.08
    Trump
    0.07
     NY
    0.07
     Ivanka
    0.07
     Tower
    0.07
     Golf
    0.07
     Signature
    0.07
     Kushner
    0.06
    egl
    0.06
     Melania
    0.06
    Activations Density 0.061%

    No Known Activations