© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125926
    Prev
    Next
    INDEX
    Explanations

    references to diplomatic agreements and conflicts, particularly involving nuclear deals

    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
     Hut
    -0.06
     Guth
    -0.06
    527
    -0.06
     Doll
    -0.06
    ulen
    -0.05
    .synthetic
    -0.05
    بات
    -0.05
    igsaw
    -0.05
     putchar
    -0.05
     snow
    -0.05
    POSITIVE LOGITS
     nuclear
    0.11
     Nuclear
    0.10
     Iran
    0.09
     Iranian
    0.09
     Iranians
    0.08
     İran
    0.08
    uclear
    0.08
     ký
    0.08
     Tehran
    0.08
     uranium
    0.07
    Activations Density 0.012%

    No Known Activations