© 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. 16136
    Prev
    Next
    INDEX
    Explanations

    references to political actions and diplomatic relations

    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
     Peel
    -0.08
     Til
    -0.06
    važ
    -0.06
    rending
    -0.06
    romise
    -0.06
    lore
    -0.06
    emark
    -0.06
    ISTA
    -0.06
     Bihar
    -0.06
    erken
    -0.06
    POSITIVE LOGITS
     Russian
    0.11
     Russia
    0.11
     russian
    0.10
     Russians
    0.10
     Russo
    0.10
    Russian
    0.09
     Kremlin
    0.09
     Moscow
    0.09
     Putin
    0.09
    Russia
    0.09
    Activations Density 0.022%

    No Known Activations