© 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. 15-LLAMASCOPE-RES-131K
    11. 103756
    Prev
    Next
    INDEX
    Explanations

    phrases related to military actions and tactics

    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
    uye
    -0.07
    ilet
    -0.07
    laus
    -0.07
    agna
    -0.07
     cannons
    -0.07
    ller
    -0.07
    á¾
    -0.07
    é²
    -0.07
    oard
    -0.06
    pth
    -0.06
    POSITIVE LOGITS
     radios
    0.07
    atori
    0.06
    -split
    0.06
    .Localization
    0.06
    issions
    0.06
    .party
    0.06
    jni
    0.06
    wire
    0.06
     mission
    0.06
    ,cp
    0.06
    Activations Density 0.019%

    No Known Activations