© 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. 87173
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical conflicts and alliances

    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
     impro
    -0.06
     nearest
    -0.06
    idine
    -0.05
     Nguyen
    -0.05
     modest
    -0.05
     Franken
    -0.05
     Urban
    -0.05
    ça
    -0.05
    UNG
    -0.05
    amp
    -0.05
    POSITIVE LOGITS
    æ¯Ĵ
    0.07
     rÃłng
    0.07
    íĸ¥
    0.07
     ÑģÑĤо
    0.07
     baise
    0.07
    .TR
    0.07
    RuleContext
    0.07
     Güven
    0.07
    relay
    0.07
    .foundation
    0.07
    Activations Density 0.002%

    No Known Activations