© 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. 83971
    Prev
    Next
    INDEX
    Explanations

    content related to military actions and geopolitical tensions

    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
    ksen
    -0.06
     fractional
    -0.06
    hte
    -0.06
    Ī¬
    -0.06
     City
    -0.06
    stad
    -0.06
    &E
    -0.06
    ddit
    -0.06
    reon
    -0.06
     Faction
    -0.06
    POSITIVE LOGITS
    ayout
    0.07
    idla
    0.06
    .enumer
    0.06
    rength
    0.06
    akeup
    0.06
     ///<
    0.06
    _multiply
    0.06
    ÏĦοι
    0.06
    =explode
    0.06
    æ°ijæĹı
    0.06
    Activations Density 0.021%

    No Known Activations