© 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. 87134
    Prev
    Next
    INDEX
    Explanations

    references to historical wars and their consequences

    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
    avax
    -0.07
    oron
    -0.07
    enko
    -0.06
     Jeg
    -0.06
    amework
    -0.06
    ihar
    -0.06
    skirts
    -0.06
    entine
    -0.06
    getInstance
    -0.06
     straight
    -0.06
    POSITIVE LOGITS
    191
    0.09
     WW
    0.07
     Europe
    0.07
     World
    0.07
     ëĮĢìłĦ
    0.07
    192
    0.07
     war
    0.07
    193
    0.06
     selber
    0.06
     European
    0.06
    Activations Density 0.085%

    No Known Activations