© 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. 55928
    Prev
    Next
    INDEX
    Explanations

    references to political organizations and their actions

    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
    upo
    -0.08
    ibu
    -0.08
    ona
    -0.07
    Æ¡
    -0.07
    ë²Į
    -0.07
    AppState
    -0.07
    HLT
    -0.07
    iese
    -0.07
    centre
    -0.07
    etheus
    -0.07
    POSITIVE LOGITS
     feu
    0.07
     Hamas
    0.06
     shower
    0.06
     prep
    0.05
     belie
    0.05
    flix
    0.05
     threatening
    0.05
     Sole
    0.05
     Shel
    0.05
     rockets
    0.05
    Activations Density 0.121%

    No Known Activations