© 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. 84445
    Prev
    Next
    INDEX
    Explanations

    terminology related to conflict resolution and international 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
    istrovstvÃŃ
    -0.08
    brane
    -0.07
    ÐļТ
    -0.07
    uga
    -0.07
    annis
    -0.07
    actionDate
    -0.06
    leh
    -0.06
     Ih
    -0.06
    ози
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
     resolution
    0.15
     resolving
    0.14
    -resolution
    0.13
     resolve
    0.12
     dispute
    0.11
     resolver
    0.11
     Resolution
    0.11
     resolutions
    0.11
     Resolver
    0.11
    resolve
    0.11
    Activations Density 0.067%

    No Known Activations