© 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. 126866
    Prev
    Next
    INDEX
    Explanations

    phrases indicating scenarios or events related to conflict and military actions

    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
    aran
    -0.07
    /stretch
    -0.07
     ((((
    -0.07
     moci
    -0.07
    /framework
    -0.07
    umar
    -0.06
    .toJSON
    -0.06
    ais
    -0.06
    ä¿Ŀéļľ
    -0.06
    /network
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.09
     contrario
    0.07
     continued
    0.07
     slightest
    0.07
    isphere
    0.07
    až
    0.06
    pedia
    0.06
     encountering
    0.06
     Marino
    0.06
     absence
    0.06
    Activations Density 0.009%

    No Known Activations